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

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

Neuron 4197 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0002

Data Index: 924305 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0321. Min Act: -0.0002

Data Index: 689522 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0246. Min Act: -0.0002

Data Index: 567123 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1265887 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0248. Min Act: -0.0002

Data Index: 345613 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0234. Min Act: -0.0002

Data Index: 113064 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0201. Min Act: -0.0002

Data Index: 299164 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0232. Min Act: -0.0002

Data Index: 59890 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0243. Min Act: -0.0002

Data Index: 304439 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0231. Min Act: -0.0002

Data Index: 638539 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0243. Min Act: -0.0002

Data Index: 420621 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0204. Min Act: -0.0002

Data Index: 847199 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1505100 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0222. Min Act: -0.0002

Data Index: 292471 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0223. Min Act: -0.0002

Data Index: 477593 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0216. Min Act: -0.0002

Data Index: 807488 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1110766 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0201. Min Act: -0.0002

Data Index: 632816 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1205287 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1358742 (C4 (Web Text))

Max Activating Token Index: 764