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

Dataset: The Pile

Neuron 4433 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: 1.5826. Min Range: -1.5826

Max Act: 1.5826. Min Act: -0.0000

Data Index: 152733 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.4035. Min Act: -0.0000

Data Index: 1226367 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.2994. Min Act: -0.0000

Data Index: 277673 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.1879. Min Act: -0.0000

Data Index: 633817 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1582520 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.2592. Min Act: -0.0000

Data Index: 287714 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.1576. Min Act: -0.0000

Data Index: 502312 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1129808 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1689460 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1321834 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0713. Min Act: -0.0000

Data Index: 611951 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.1353. Min Act: -0.0000

Data Index: 1053482 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 1.5826. Min Range: -1.5826

Max Act: 0.9977. Min Act: -0.0000

Data Index: 425593 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1475035 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0449. Min Act: -0.0000

Data Index: 1166250 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 1.5826. Min Range: -1.5826

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1224524 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1807965 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.0622. Min Act: -0.0000

Data Index: 200466 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 1.5826. Min Range: -1.5826

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1999758 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.5826. Min Range: -1.5826

Max Act: 0.9636. Min Act: -0.0000

Data Index: 259897 (The Pile)

Max Activating Token Index: 168