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

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

Neuron 1597 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: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1158010 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0821. Min Act: -0.0002

Data Index: 239449 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1067103 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0772. Min Act: -0.0002

Data Index: 336795 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1283555 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0714. Min Act: -0.0002

Data Index: 474589 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1173455 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1256724 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0741. Min Act: -0.0002

Data Index: 316245 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1036452 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0655. Min Act: -0.0002

Data Index: 782096 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0626. Min Act: -0.0002

Data Index: 261407 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0647. Min Act: -0.0002

Data Index: 616371 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0635. Min Act: -0.0002

Data Index: 56210 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0630. Min Act: -0.0002

Data Index: 97956 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0625. Min Act: -0.0002

Data Index: 148532 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0619. Min Act: -0.0002

Data Index: 665780 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0637. Min Act: -0.0002

Data Index: 999488 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0616. Min Act: -0.0002

Data Index: 658087 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0631. Min Act: -0.0002

Data Index: 292570 (C4 (Web Text))

Max Activating Token Index: 656