Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 139 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1304975 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0252. Min Act: -0.0006

Data Index: 343340 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1247603 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0243. Min Act: -0.0006

Data Index: 375247 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0241. Min Act: -0.0006

Data Index: 378506 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1163391 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1042484 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0239. Min Act: -0.0006

Data Index: 44655 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0234. Min Act: -0.0006

Data Index: 741383 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1253105 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0235. Min Act: -0.0006

Data Index: 276824 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0229. Min Act: -0.0006

Data Index: 426582 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0233. Min Act: -0.0006

Data Index: 329346 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1038136 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1325714 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0232. Min Act: -0.0006

Data Index: 607206 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0221. Min Act: -0.0006

Data Index: 85994 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0223. Min Act: -0.0006

Data Index: 606230 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1225848 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0223. Min Act: -0.0006

Data Index: 599734 (C4 (Web Text))

Max Activating Token Index: 924