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

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

Neuron 415 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: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0002

Data Index: 488799 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0402. Min Act: -0.0003

Data Index: 404078 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0004

Data Index: 706782 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1229049 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1211977 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0401. Min Act: -0.0003

Data Index: 806042 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0396. Min Act: -0.0003

Data Index: 277660 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1283523 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0392. Min Act: -0.0003

Data Index: 826115 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0391. Min Act: -0.0003

Data Index: 480256 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0383. Min Act: -0.0003

Data Index: 510090 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0375. Min Act: -0.0003

Data Index: 882186 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0374. Min Act: -0.0004

Data Index: 821392 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0388. Min Act: -0.0003

Data Index: 33564 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0364. Min Act: -0.0002

Data Index: 941082 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0371. Min Act: -0.0002

Data Index: 938709 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0376. Min Act: -0.0003

Data Index: 931214 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0371. Min Act: -0.0003

Data Index: 684364 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0347. Min Act: -0.0004

Data Index: 765996 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1277153 (C4 (Web Text))

Max Activating Token Index: 598