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

Dataset: The Pile

Neuron 571 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: 1.0971. Min Range: -1.0971

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1581380 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1950494 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1279022 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8763. Min Act: -0.0000

Data Index: 536941 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9059. Min Act: -0.0000

Data Index: 788592 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1877205 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9279. Min Act: -0.0000

Data Index: 939430 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1304757 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1717706 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1621312 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1740198 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8751. Min Act: -0.0000

Data Index: 910131 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8175. Min Act: -0.0000

Data Index: 721676 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1431705 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.7821. Min Act: -0.0000

Data Index: 270047 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1724515 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1553072 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1783906 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.7292. Min Act: -0.0000

Data Index: 251941 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8177. Min Act: -0.0000

Data Index: 85940 (The Pile)

Max Activating Token Index: 577