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

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

Neuron 3304 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0524. Min Range: -8.0524

Max Act: 8.0524. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.8296. Min Act: -0.0000

Data Index: 917725 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.3526. Min Act: -0.0000

Data Index: 1098604 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.4909. Min Act: -0.0000

Data Index: 932188 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.3000. Min Act: -0.0000

Data Index: 775987 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.2045. Min Act: -0.0000

Data Index: 169054 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.4572. Min Act: -0.0000

Data Index: 1249697 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.8704. Min Act: -0.0000

Data Index: 661402 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.9800. Min Act: -0.0000

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.1782. Min Act: -0.0000

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.7277. Min Act: -0.0000

Data Index: 601478 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 8.0524. Min Range: -8.0524

Max Act: 7.0431. Min Act: -0.0000

Data Index: 1288599 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.9989. Min Act: -0.0000

Data Index: 162768 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.3485. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.3286. Min Act: -0.0000

Data Index: 1052989 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.3155. Min Act: -0.0000

Data Index: 729151 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.5314. Min Act: -0.0000

Data Index: 1035178 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.6764. Min Act: -0.0000

Data Index: 914770 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.3043. Min Act: -0.0000

Data Index: 497986 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 8.0524. Min Range: -8.0524

Max Act: 6.2774. Min Act: -0.0000

Data Index: 103254 (C4 (Web Text))

Max Activating Token Index: 166