Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2475 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.8396. Min Act: -0.0000

Data Index: 1010366 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.3470. Min Act: -0.0000

Data Index: 898293 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.4135. Min Act: -0.0000

Data Index: 1122846 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.2623. Min Act: -0.0000

Data Index: 1315444 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.2560. Min Act: -0.0000

Data Index: 171629 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.2024. Min Act: -0.0000

Data Index: 568938 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.0746. Min Act: -0.0000

Data Index: 685624 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.0409. Min Act: -0.0000

Data Index: 905204 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.8228. Min Act: -0.0000

Data Index: 462157 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.9196. Min Act: -0.0000

Data Index: 1119899 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.9178. Min Act: -0.0000

Data Index: 1200565 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.9196. Min Act: -0.0000

Data Index: 121747 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 2.8396. Min Range: -2.8396

Max Act: 2.0228. Min Act: -0.0000

Data Index: 16090 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.7923. Min Act: -0.0000

Data Index: 94327 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1144988 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.8497. Min Act: -0.0000

Data Index: 789302 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.8255. Min Act: -0.0000

Data Index: 943078 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.7815. Min Act: -0.0000

Data Index: 542867 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.8836. Min Act: -0.0000

Data Index: 1009893 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 2.8396. Min Range: -2.8396

Max Act: 1.7672. Min Act: -0.0000

Data Index: 794830 (C4 (Web Text))

Max Activating Token Index: 818