Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 319 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1353357 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0226. Min Act: -0.0006

Data Index: 414157 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0220. Min Act: -0.0006

Data Index: 480103 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0216. Min Act: -0.0006

Data Index: 738064 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0215. Min Act: -0.0006

Data Index: 351808 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0219. Min Act: -0.0006

Data Index: 484931 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1240420 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0219. Min Act: -0.0006

Data Index: 962121 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1166511 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0198. Min Act: -0.0006

Data Index: 725980 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1042150 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0220. Min Act: -0.0006

Data Index: 485959 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0207. Min Act: -0.0006

Data Index: 861804 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0211. Min Act: -0.0006

Data Index: 112828 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0211. Min Act: -0.0006

Data Index: 569330 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0202. Min Act: -0.0006

Data Index: 914217 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0206. Min Act: -0.0005

Data Index: 1059303 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0206. Min Act: -0.0006

Data Index: 439992 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0205. Min Act: -0.0006

Data Index: 62837 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0210. Min Act: -0.0006

Data Index: 43271 (C4 (Web Text))

Max Activating Token Index: 299