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

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

Neuron 3192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0383. Min Act: -0.0002

Data Index: 102598 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1270364 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1126116 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1233732 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1107457 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0346. Min Act: -0.0002

Data Index: 188115 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1165654 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0329. Min Act: -0.0002

Data Index: 874925 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1247335 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0339. Min Act: -0.0002

Data Index: 972476 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0342. Min Act: -0.0002

Data Index: 992968 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0340. Min Act: -0.0002

Data Index: 479661 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1079520 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0322. Min Act: -0.0002

Data Index: 3214 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0333. Min Act: -0.0002

Data Index: 50530 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0312. Min Act: -0.0002

Data Index: 426157 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0312. Min Act: -0.0002

Data Index: 777488 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0295. Min Act: -0.0002

Data Index: 376511 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0301. Min Act: -0.0002

Data Index: 508986 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0306. Min Act: -0.0002

Data Index: 216028 (C4 (Web Text))

Max Activating Token Index: 229