Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2062 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4164. Min Range: -3.4164

Max Act: 3.4164. Min Act: -0.0000

Data Index: 352955 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 3.4164. Min Range: -3.4164

Max Act: 3.1990. Min Act: -0.0000

Data Index: 1936287 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 3.4164. Min Range: -3.4164

Max Act: 3.2328. Min Act: -0.0000

Data Index: 388276 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 3.4164. Min Range: -3.4164

Max Act: 3.1276. Min Act: -0.0000

Data Index: 72967 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.8217. Min Act: -0.0000

Data Index: 1806148 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 3.4164. Min Range: -3.4164

Max Act: 3.2082. Min Act: -0.0000

Data Index: 118000 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 3.4164. Min Range: -3.4164

Max Act: 3.0414. Min Act: -0.0000

Data Index: 1391278 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.6954. Min Act: -0.0000

Data Index: 1986200 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 3.4164. Min Range: -3.4164

Max Act: 3.1231. Min Act: -0.0000

Data Index: 469110 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9792. Min Act: -0.0000

Data Index: 1089314 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9657. Min Act: -0.0000

Data Index: 293042 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9766. Min Act: -0.0000

Data Index: 289652 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.7995. Min Act: -0.0000

Data Index: 268790 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9413. Min Act: -0.0000

Data Index: 380484 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9457. Min Act: -0.0000

Data Index: 1244411 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9554. Min Act: -0.0000

Data Index: 914582 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9518. Min Act: -0.0000

Data Index: 1996087 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.9304. Min Act: -0.0000

Data Index: 818574 (The Pile)

Max Activating Token Index: 620

Text #18

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.7806. Min Act: -0.0000

Data Index: 1398782 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 3.4164. Min Range: -3.4164

Max Act: 2.8961. Min Act: -0.0000

Data Index: 1094423 (The Pile)

Max Activating Token Index: 52