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

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

Neuron 142 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: 0.0262. Min Range: -0.0262

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1253561 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0231. Min Act: -0.0006

Data Index: 802314 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0236. Min Act: -0.0006

Data Index: 97305 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0221. Min Act: -0.0006

Data Index: 787904 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1352908 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1003233 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0212. Min Act: -0.0006

Data Index: 960417 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0217. Min Act: -0.0006

Data Index: 467268 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0217. Min Act: -0.0006

Data Index: 950958 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0211. Min Act: -0.0006

Data Index: 77316 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0208. Min Act: -0.0006

Data Index: 868216 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0194. Min Act: -0.0006

Data Index: 203803 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0207. Min Act: -0.0006

Data Index: 825506 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0212. Min Act: -0.0006

Data Index: 359243 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0221. Min Act: -0.0006

Data Index: 805040 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1264495 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0195. Min Act: -0.0006

Data Index: 543394 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0204. Min Act: -0.0006

Data Index: 41888 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0211. Min Act: -0.0006

Data Index: 804587 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0206. Min Act: -0.0006

Data Index: 413398 (C4 (Web Text))

Max Activating Token Index: 569