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

Dataset: The Pile

Neuron 3240 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1542725 (The Pile)

Max Activating Token Index: 969

Text #1

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.4351. Min Act: -0.0000

Data Index: 307670 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1434568 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1395540 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1112648 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3897. Min Act: -0.0000

Data Index: 29177 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3868. Min Act: -0.0000

Data Index: 488686 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1406741 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3602. Min Act: -0.0000

Data Index: 936400 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1690977 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3682. Min Act: -0.0000

Data Index: 719321 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1918240 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1126331 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3447. Min Act: -0.0000

Data Index: 442311 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3190. Min Act: -0.0000

Data Index: 915510 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1331072 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1947734 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1631728 (The Pile)

Max Activating Token Index: 339

Text #18

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1471847 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3317. Min Act: -0.0000

Data Index: 306767 (The Pile)

Max Activating Token Index: 883