Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1462 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3335. Min Act: -0.0000

Data Index: 747965 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1100656 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2753. Min Act: -0.0000

Data Index: 97998 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3033. Min Act: -0.0000

Data Index: 226906 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2845. Min Act: -0.0000

Data Index: 238284 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1172370 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2558. Min Act: -0.0000

Data Index: 682497 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1074377 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2614. Min Act: -0.0000

Data Index: 218521 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1013132 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1198621 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2190. Min Act: -0.0000

Data Index: 428902 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2484. Min Act: -0.0000

Data Index: 596611 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2400. Min Act: -0.0000

Data Index: 606403 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2370. Min Act: -0.0000

Data Index: 965452 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2404. Min Act: -0.0000

Data Index: 611654 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2270. Min Act: -0.0000

Data Index: 403463 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2238. Min Act: -0.0000

Data Index: 73991 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1212626 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2213. Min Act: -0.0000

Data Index: 585965 (C4 (Web Text))

Max Activating Token Index: 321