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

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

Neuron 2084 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7606. Min Act: -0.0000

Data Index: 1167274 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.4099. Min Act: -0.0000

Data Index: 735609 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.3960. Min Act: -0.0000

Data Index: 21274 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.5171. Min Act: -0.0000

Data Index: 614200 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.3870. Min Act: -0.0000

Data Index: 1088715 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.1174. Min Act: -0.0000

Data Index: 1072458 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.1645. Min Act: -0.0000

Data Index: 1295330 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.2724. Min Act: -0.0000

Data Index: 714238 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 2.7606. Min Range: -2.7606

Max Act: 1.9039. Min Act: -0.0000

Data Index: 1052268 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.0523. Min Act: -0.0000

Data Index: 742054 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.0367. Min Act: -0.0000

Data Index: 112199 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.0195. Min Act: -0.0000

Data Index: 1502016 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 2.7606. Min Range: -2.7606

Max Act: 1.9237. Min Act: -0.0000

Data Index: 630790 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1203466 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 2.7606. Min Range: -2.7606

Max Act: 1.8825. Min Act: -0.0000

Data Index: 489748 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 2.7606. Min Range: -2.7606

Max Act: 1.8585. Min Act: -0.0000

Data Index: 17735 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.0629. Min Act: -0.0000

Data Index: 13756 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.0519. Min Act: -0.0000

Data Index: 196465 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 2.7606. Min Range: -2.7606

Max Act: 1.8087. Min Act: -0.0000

Data Index: 416919 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.1431. Min Act: -0.0000

Data Index: 383555 (C4 (Web Text))

Max Activating Token Index: 134