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

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

Neuron 1694 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0002

Data Index: 36801 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0714. Min Act: -0.0002

Data Index: 70433 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0666. Min Act: -0.0002

Data Index: 484932 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0648. Min Act: -0.0002

Data Index: 996096 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0596. Min Act: -0.0002

Data Index: 5282 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1102946 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0579. Min Act: -0.0002

Data Index: 454785 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0550. Min Act: -0.0002

Data Index: 877696 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1018955 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1262348 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0541. Min Act: -0.0002

Data Index: 800173 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0516. Min Act: -0.0002

Data Index: 97041 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1081770 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0516. Min Act: -0.0002

Data Index: 750137 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0511. Min Act: -0.0002

Data Index: 402498 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1162167 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0521. Min Act: -0.0002

Data Index: 327433 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0517. Min Act: -0.0002

Data Index: 241848 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0490. Min Act: -0.0002

Data Index: 297001 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0501. Min Act: -0.0002

Data Index: 899398 (C4 (Web Text))

Max Activating Token Index: 407