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

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

Neuron 748 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0003

Data Index: 531549 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1425771 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0376. Min Act: -0.0003

Data Index: 740421 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0380. Min Act: -0.0003

Data Index: 166011 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0376. Min Act: -0.0003

Data Index: 574347 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0385. Min Act: -0.0003

Data Index: 875419 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1303994 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0363. Min Act: -0.0003

Data Index: 141756 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0369. Min Act: -0.0003

Data Index: 281269 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0360. Min Act: -0.0003

Data Index: 797454 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0363. Min Act: -0.0002

Data Index: 492180 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0345. Min Act: -0.0003

Data Index: 252777 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1186469 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0360. Min Act: -0.0003

Data Index: 214421 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0355. Min Act: -0.0004

Data Index: 442636 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0348. Min Act: -0.0003

Data Index: 652845 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0348. Min Act: -0.0002

Data Index: 942424 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1134726 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0335. Min Act: -0.0003

Data Index: 281125 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0340. Min Act: -0.0003

Data Index: 472568 (C4 (Web Text))

Max Activating Token Index: 562