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

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

Neuron 4004 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0002

Data Index: 291398 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0246. Min Act: -0.0002

Data Index: 735312 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1205540 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0238. Min Act: -0.0002

Data Index: 694929 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0228. Min Act: -0.0002

Data Index: 442977 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0224. Min Act: -0.0002

Data Index: 448754 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0223. Min Act: -0.0002

Data Index: 16911 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0227. Min Act: -0.0002

Data Index: 988225 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0228. Min Act: -0.0002

Data Index: 378817 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0002

Data Index: 195035 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1444683 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0002

Data Index: 178808 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1302943 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1552931 (Python Code)

Max Activating Token Index: 505

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0211. Min Act: -0.0002

Data Index: 322485 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0206. Min Act: -0.0002

Data Index: 573469 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0205. Min Act: -0.0002

Data Index: 833637 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0204. Min Act: -0.0002

Data Index: 471586 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0206. Min Act: -0.0002

Data Index: 821836 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0197. Min Act: -0.0002

Data Index: 972979 (C4 (Web Text))

Max Activating Token Index: 20