Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1649. Min Range: -1.1649

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1011159 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 1.1649. Min Range: -1.1649

Max Act: 1.0561. Min Act: -0.0000

Data Index: 622574 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.1649. Min Range: -1.1649

Max Act: 1.0240. Min Act: -0.0000

Data Index: 662002 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 1.1649. Min Range: -1.1649

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1869989 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 1.1649. Min Range: -1.1649

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1011478 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1772611 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1707936 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1411676 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8524. Min Act: -0.0000

Data Index: 681424 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9443. Min Act: -0.0000

Data Index: 549695 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8695. Min Act: -0.0000

Data Index: 747940 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8998. Min Act: -0.0000

Data Index: 498904 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9381. Min Act: -0.0000

Data Index: 489435 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8222. Min Act: -0.0000

Data Index: 586301 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1896213 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8287. Min Act: -0.0000

Data Index: 231039 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8654. Min Act: -0.0000

Data Index: 88025 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1447250 (The Pile)

Max Activating Token Index: 620

Text #18

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8383. Min Act: -0.0000

Data Index: 910804 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1994811 (The Pile)

Max Activating Token Index: 958