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

Dataset: The Pile

Neuron 1403 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1514385 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1966. Min Act: -0.0000

Data Index: 483013 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9514. Min Act: -0.0000

Data Index: 760351 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1580698 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9422. Min Act: -0.0000

Data Index: 726785 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8512. Min Act: -0.0000

Data Index: 412516 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8759. Min Act: -0.0000

Data Index: 179433 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8840. Min Act: -0.0000

Data Index: 773626 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1701680 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1977526 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8319. Min Act: -0.0000

Data Index: 109608 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1001560 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8223. Min Act: -0.0000

Data Index: 451745 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1940135 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1634107 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1833447 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1749017 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1650503 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.7911. Min Act: -0.0000

Data Index: 191685 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1671921 (The Pile)

Max Activating Token Index: 87