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

Dataset: The Pile

Neuron 902 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5064. Min Act: -0.0000

Data Index: 733 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1264008 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5948. Min Act: -0.0000

Data Index: 484444 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6168. Min Act: -0.0000

Data Index: 674722 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1083017 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5141. Min Act: -0.0000

Data Index: 642319 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1562334 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1723116 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1964960 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1102805 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5326. Min Act: -0.0000

Data Index: 695295 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.4744. Min Act: -0.0000

Data Index: 906215 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.4601. Min Act: -0.0000

Data Index: 264805 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.4123. Min Act: -0.0000

Data Index: 489438 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1329146 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.4377. Min Act: -0.0000

Data Index: 628970 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1037478 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1513133 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5602. Min Act: -0.0000

Data Index: 685712 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1920860 (The Pile)

Max Activating Token Index: 240