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

Dataset: The Pile

Neuron 6 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: 0.2665. Min Range: -0.2665

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1584968 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2473. Min Act: -0.0000

Data Index: 918934 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2147. Min Act: -0.0000

Data Index: 435082 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2254. Min Act: -0.0000

Data Index: 232847 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1527322 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2059. Min Act: -0.0000

Data Index: 956300 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1640360 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1421814 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1812. Min Act: -0.0000

Data Index: 418583 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1808. Min Act: -0.0000

Data Index: 129933 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1273379 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1954755 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1290918 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1054102 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1678. Min Act: -0.0000

Data Index: 194167 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1579. Min Act: -0.0000

Data Index: 215301 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1583393 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1652. Min Act: -0.0000

Data Index: 827489 (The Pile)

Max Activating Token Index: 292

Text #18

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1750. Min Act: -0.0000

Data Index: 979969 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1655. Min Act: -0.0000

Data Index: 528069 (The Pile)

Max Activating Token Index: 19