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

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

Neuron 14 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: 0.4473. Min Range: -0.4473

Max Act: 0.4473. Min Act: -0.0000

Data Index: 63230 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3572. Min Act: -0.0000

Data Index: 146148 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3333. Min Act: 0.0000

Data Index: 159782 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1332741 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3226. Min Act: -0.0000

Data Index: 802997 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3441. Min Act: -0.0000

Data Index: 818114 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3159. Min Act: 0.0000

Data Index: 1192084 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1094966 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3066. Min Act: -0.0000

Data Index: 751386 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3234. Min Act: -0.0000

Data Index: 989669 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.3022. Min Act: -0.0000

Data Index: 789263 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2935. Min Act: -0.0000

Data Index: 389151 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2891. Min Act: -0.0000

Data Index: 863390 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2873. Min Act: -0.0000

Data Index: 145354 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2913. Min Act: -0.0000

Data Index: 798403 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2887. Min Act: -0.0000

Data Index: 22091 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2773. Min Act: -0.0000

Data Index: 492566 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2843. Min Act: 0.0000

Data Index: 434084 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2790. Min Act: -0.0000

Data Index: 56858 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.4473. Min Range: -0.4473

Max Act: 0.2672. Min Act: -0.0000

Data Index: 168809 (C4 (Web Text))

Max Activating Token Index: 785