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

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

Neuron 3769 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: 1.4191. Min Range: -1.4191

Max Act: 1.4191. Min Act: -0.0000

Data Index: 712787 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.3328. Min Act: -0.0000

Data Index: 665100 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.1530. Min Act: 0.0000

Data Index: 280779 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1005450 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.2425. Min Act: -0.0000

Data Index: 950233 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.1359. Min Act: -0.0000

Data Index: 660659 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.0769. Min Act: -0.0000

Data Index: 225299 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1089331 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9716. Min Act: 0.0000

Data Index: 717699 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1156868 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.0261. Min Act: 0.0000

Data Index: 1095379 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.0097. Min Act: -0.0000

Data Index: 94390 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9432. Min Act: -0.0000

Data Index: 125995 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9403. Min Act: -0.0000

Data Index: 225007 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9816. Min Act: 0.0000

Data Index: 76947 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1033228 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8579. Min Act: 0.0000

Data Index: 420570 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1143682 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.7637. Min Act: -0.0000

Data Index: 886255 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8105. Min Act: 0.0000

Data Index: 1156729 (C4 (Web Text))

Max Activating Token Index: 389