Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2646 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4854. Min Act: -0.0000

Data Index: 637970 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1245526 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1128369 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3908. Min Act: -0.0000

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1262392 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3966. Min Act: -0.0000

Data Index: 885568 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3885. Min Act: -0.0000

Data Index: 879875 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3534. Min Act: -0.0000

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3361. Min Act: -0.0000

Data Index: 564839 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3466. Min Act: -0.0000

Data Index: 820429 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3503. Min Act: -0.0000

Data Index: 58777 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3378. Min Act: -0.0000

Data Index: 140162 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3303. Min Act: -0.0000

Data Index: 806619 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3614. Min Act: -0.0000

Data Index: 726476 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3321. Min Act: -0.0000

Data Index: 602493 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3171. Min Act: -0.0000

Data Index: 650027 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3254. Min Act: -0.0000

Data Index: 718509 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3359. Min Act: -0.0000

Data Index: 54193 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3092. Min Act: -0.0000

Data Index: 787207 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3250. Min Act: -0.0000

Data Index: 43591 (C4 (Web Text))

Max Activating Token Index: 326