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

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

Neuron 3421 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.8982. Min Act: -0.0000

Data Index: 1282053 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 5.0948. Min Range: -5.0948

Max Act: 5.0948. Min Act: -0.0000

Data Index: 281730 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.7063. Min Act: -0.0000

Data Index: 961870 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.6638. Min Act: -0.0000

Data Index: 850759 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.7310. Min Act: -0.0000

Data Index: 285287 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.7198. Min Act: -0.0000

Data Index: 483743 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.4944. Min Act: -0.0000

Data Index: 1008002 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.2499. Min Act: -0.0000

Data Index: 288333 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.3769. Min Act: -0.0000

Data Index: 345709 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.3170. Min Act: -0.0000

Data Index: 473396 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.2257. Min Act: -0.0000

Data Index: 559808 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 5.0948. Min Range: -5.0948

Max Act: 3.7664. Min Act: -0.0000

Data Index: 22585 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.1859. Min Act: -0.0000

Data Index: 337403 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 5.0948. Min Range: -5.0948

Max Act: 3.8178. Min Act: -0.0000

Data Index: 807531 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 5.0948. Min Range: -5.0948

Max Act: 3.9478. Min Act: -0.0000

Data Index: 793089 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 5.0948. Min Range: -5.0948

Max Act: 4.0943. Min Act: -0.0000

Data Index: 714929 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 5.0948. Min Range: -5.0948

Max Act: 3.9034. Min Act: -0.0000

Data Index: 563750 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 5.0948. Min Range: -5.0948

Max Act: 3.6757. Min Act: -0.0000

Data Index: 1236623 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 5.0948. Min Range: -5.0948

Max Act: 3.8371. Min Act: -0.0000

Data Index: 33914 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 5.0948. Min Range: -5.0948

Max Act: 3.8207. Min Act: -0.0000

Data Index: 754826 (C4 (Web Text))

Max Activating Token Index: 741