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

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

Neuron 32 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: 0.8479. Min Range: -0.8479

Max Act: 0.8113. Min Act: -0.0000

Data Index: 755985 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.8479. Min Act: -0.0000

Data Index: 572610 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1157747 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1300589 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6371. Min Act: -0.0000

Data Index: 706691 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5959. Min Act: -0.0000

Data Index: 729502 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5866. Min Act: -0.0000

Data Index: 187583 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6028. Min Act: -0.0000

Data Index: 452812 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1136546 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1278995 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5360. Min Act: -0.0000

Data Index: 896356 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5219. Min Act: -0.0000

Data Index: 870621 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1249398 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.4816. Min Act: -0.0000

Data Index: 669271 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5362. Min Act: -0.0000

Data Index: 676267 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.4091. Min Act: -0.0000

Data Index: 22536 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.4516. Min Act: -0.0000

Data Index: 795268 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.4698. Min Act: -0.0000

Data Index: 570113 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.4392. Min Act: -0.0000

Data Index: 584726 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.3774. Min Act: -0.0000

Data Index: 984668 (C4 (Web Text))

Max Activating Token Index: 989