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

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

Neuron 808 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: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0006

Data Index: 201421 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0261. Min Act: -0.0006

Data Index: 815626 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1121817 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1164077 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0253. Min Act: -0.0006

Data Index: 602549 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0247. Min Act: -0.0006

Data Index: 614161 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1187968 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0240. Min Act: -0.0006

Data Index: 46025 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0246. Min Act: -0.0006

Data Index: 604271 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0234. Min Act: -0.0006

Data Index: 672982 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1204710 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0257. Min Act: -0.0006

Data Index: 277387 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0229. Min Act: -0.0006

Data Index: 113992 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1185213 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0231. Min Act: -0.0006

Data Index: 957185 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0231. Min Act: -0.0006

Data Index: 505613 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0228. Min Act: -0.0006

Data Index: 55501 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0228. Min Act: -0.0006

Data Index: 467485 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1193003 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0006

Data Index: 162399 (C4 (Web Text))

Max Activating Token Index: 396