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

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

Neuron 1854 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1021027 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1566225 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0246. Min Act: -0.0002

Data Index: 564449 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1168696 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0243. Min Act: -0.0002

Data Index: 668000 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0235. Min Act: -0.0002

Data Index: 586830 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1616991 (Python Code)

Max Activating Token Index: 352

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0235. Min Act: -0.0002

Data Index: 462504 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0226. Min Act: -0.0002

Data Index: 141262 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1195450 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0225. Min Act: -0.0002

Data Index: 412933 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0223. Min Act: -0.0002

Data Index: 470071 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1547093 (Python Code)

Max Activating Token Index: 614

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0227. Min Act: -0.0002

Data Index: 91546 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1455226 (Python Code)

Max Activating Token Index: 251

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1456323 (Python Code)

Max Activating Token Index: 659

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0216. Min Act: -0.0003

Data Index: 7288 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1423951 (Python Code)

Max Activating Token Index: 715

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0215. Min Act: -0.0002

Data Index: 293178 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0219. Min Act: -0.0002

Data Index: 125199 (C4 (Web Text))

Max Activating Token Index: 514