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

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

Neuron 1906 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: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0006

Data Index: 679013 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0341. Min Act: -0.0006

Data Index: 291532 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0290. Min Act: -0.0006

Data Index: 790662 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0277. Min Act: -0.0006

Data Index: 286144 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1054475 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1281495 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1345575 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0285. Min Act: -0.0006

Data Index: 205910 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0278. Min Act: -0.0006

Data Index: 88420 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0278. Min Act: -0.0006

Data Index: 315647 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0282. Min Act: -0.0006

Data Index: 621837 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0261. Min Act: -0.0006

Data Index: 796018 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0284. Min Act: -0.0006

Data Index: 895298 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1357795 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1264068 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0274. Min Act: -0.0006

Data Index: 504556 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0274. Min Act: -0.0006

Data Index: 919064 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0280. Min Act: -0.0006

Data Index: 682930 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0274. Min Act: -0.0006

Data Index: 94469 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0278. Min Act: -0.0006

Data Index: 654827 (C4 (Web Text))

Max Activating Token Index: 462