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

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

Neuron 426 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.6493. Min Range: -10.6493

Max Act: 10.6493. Min Act: 0.0001

Data Index: 1139244 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 10.6493. Min Range: -10.6493

Max Act: 8.5737. Min Act: -0.0000

Data Index: 540032 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.9530. Min Act: -0.0000

Data Index: 1026070 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 10.6493. Min Range: -10.6493

Max Act: 8.2997. Min Act: -0.0000

Data Index: 59956 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.8763. Min Act: -0.0000

Data Index: 814715 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 10.6493. Min Range: -10.6493

Max Act: 8.0537. Min Act: -0.0000

Data Index: 710437 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.6355. Min Act: -0.0000

Data Index: 1256588 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.7759. Min Act: -0.0000

Data Index: 1233083 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.2349. Min Act: -0.0000

Data Index: 855711 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.2191. Min Act: -0.0000

Data Index: 977212 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 10.6493. Min Range: -10.6493

Max Act: 6.9927. Min Act: -0.0000

Data Index: 722289 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.3399. Min Act: -0.0000

Data Index: 338780 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.1354. Min Act: -0.0000

Data Index: 1175012 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.2646. Min Act: -0.0000

Data Index: 505451 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.2696. Min Act: -0.0000

Data Index: 1279711 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.1214. Min Act: -0.0000

Data Index: 1069833 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.0801. Min Act: 0.0000

Data Index: 406952 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 10.6493. Min Range: -10.6493

Max Act: 7.0045. Min Act: -0.0000

Data Index: 1213318 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 10.6493. Min Range: -10.6493

Max Act: 6.6086. Min Act: -0.0000

Data Index: 806932 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 10.6493. Min Range: -10.6493

Max Act: 6.9906. Min Act: -0.0000

Data Index: 246719 (C4 (Web Text))

Max Activating Token Index: 118