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

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

Neuron 4686 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: 0.7381. Min Range: -0.7381

Max Act: 0.6986. Min Act: -0.0000

Data Index: 481457 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.7381. Min Act: 0.0000

Data Index: 1357980 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.6515. Min Act: -0.0000

Data Index: 623294 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1233733 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5829. Min Act: -0.0000

Data Index: 912914 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1000181 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1326046 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1106287 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4732. Min Act: -0.0000

Data Index: 453991 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4851. Min Act: -0.0000

Data Index: 528894 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4854. Min Act: -0.0000

Data Index: 558856 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4385. Min Act: -0.0000

Data Index: 391260 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4669. Min Act: -0.0000

Data Index: 216393 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4447. Min Act: -0.0000

Data Index: 37116 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4507. Min Act: -0.0000

Data Index: 625972 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4503. Min Act: -0.0000

Data Index: 349136 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4717. Min Act: -0.0000

Data Index: 777593 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1087232 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4661. Min Act: -0.0000

Data Index: 194933 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4493. Min Act: -0.0000

Data Index: 160641 (C4 (Web Text))

Max Activating Token Index: 435