June 25, 2024
We analyze a family of large language models in such a lightweight manner that can be done on a single GPU. Specifically, we focus on the OPT family of models ranging from 125m to 66b parameters and rely only on whether an FFN neuron is activated or not. First, we find that the early part of the network is sparse and represents many discrete features. Here, many neurons (more than 70% in some layers of the 66b model) are "dead", i.e. they never activate on a large collection of diverse data. At the same time, many of the alive neurons are reserved for discrete features and act as token and n-gram detectors. Interestingly, their corresponding FFN updates not only promote next token candidates as could be expected, but also explicitly focus on removing the information about triggering them tokens, i.e., current input. To the best of our knowledge, this is the first example of mechanisms specialized at removing (rather than adding) information from the residual stream. With scale, models become more sparse in a sense that they have more dead neurons and token detectors. Finally, some neurons are positional: them being activated or not depends largely (or solely) on position and less so (or not at all) on textual data. We find that smaller models have sets of neurons acting as position range indicators while larger models operate in a less explicit manner.
Written by
Elena Voita
Javier Ferrando Monsonis
Christoforos Nalmpantis
Publisher
ARR, then ACL
Research Topics
June 25, 2024
Min-Jae Hwang, Ilia Kulikov, Benjamin Peloquin, Hongyu Gong, Peng-Jen Chen, Ann Lee
June 25, 2024
June 14, 2024
Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Scott Yih, Xilun Chen
June 14, 2024
June 14, 2024
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Nas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, Ahmed Aly, Beidi Chen, Carole-Jean Wu
June 14, 2024
June 13, 2024
Ava Spataru, Eric Hambro, Lena Voita, Nicola Cancedda
June 13, 2024
Product experiences
Foundational models
Product experiences
Latest news
Foundational models