Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2735 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.1251. Min Range: -7.1251

Max Act: 7.1251. Min Act: -0.0000

Data Index: 1082087 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 7.1251. Min Range: -7.1251

Max Act: 6.6683. Min Act: -0.0000

Data Index: 1155609 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 7.1251. Min Range: -7.1251

Max Act: 6.6546. Min Act: -0.0000

Data Index: 1038217 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 7.1251. Min Range: -7.1251

Max Act: 6.5552. Min Act: -0.0000

Data Index: 57341 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 7.1251. Min Range: -7.1251

Max Act: 6.4879. Min Act: -0.0000

Data Index: 631110 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 7.1251. Min Range: -7.1251

Max Act: 6.4671. Min Act: -0.0000

Data Index: 522684 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 7.1251. Min Range: -7.1251

Max Act: 6.4173. Min Act: -0.0000

Data Index: 1163904 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.9613. Min Act: -0.0000

Data Index: 1120114 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.0121. Min Act: -0.0000

Data Index: 889471 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.9003. Min Act: -0.0000

Data Index: 280624 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.9039. Min Act: -0.0000

Data Index: 1030263 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.7857. Min Act: -0.0000

Data Index: 1123742 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.3573. Min Act: -0.0000

Data Index: 956316 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.9220. Min Act: -0.0000

Data Index: 1252388 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.6133. Min Act: -0.0000

Data Index: 53021 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.3644. Min Act: -0.0000

Data Index: 1304741 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.6963. Min Act: -0.0000

Data Index: 1303177 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.4755. Min Act: -0.0000

Data Index: 248165 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.4742. Min Act: -0.0000

Data Index: 1089948 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 7.1251. Min Range: -7.1251

Max Act: 5.4512. Min Act: -0.0000

Data Index: 1351179 (C4 (Web Text))

Max Activating Token Index: 833