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

Dataset: The Pile

Neuron 3038 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: 0.6082. Min Range: -0.6082

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1820554 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1104975 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1847073 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.5163. Min Act: -0.0000

Data Index: 274484 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1598295 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1182351 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1389509 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1565181 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4485. Min Act: -0.0000

Data Index: 522231 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1876244 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1575065 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4181. Min Act: -0.0000

Data Index: 942834 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4185. Min Act: -0.0000

Data Index: 459036 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1238854 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4278. Min Act: -0.0000

Data Index: 568064 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4281. Min Act: -0.0000

Data Index: 486515 (The Pile)

Max Activating Token Index: 961

Text #16

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1149804 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1433407 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4226. Min Act: -0.0000

Data Index: 275559 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.6082. Min Range: -0.6082

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1746578 (The Pile)

Max Activating Token Index: 357