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

Dataset: The Pile

Neuron 1551 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: 5.6812. Min Range: -5.6812

Max Act: 5.6812. Min Act: -0.0000

Data Index: 482840 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.2597. Min Act: -0.0000

Data Index: 1975907 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.2115. Min Act: -0.0000

Data Index: 1952665 (The Pile)

Max Activating Token Index: 95

Text #3

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.3281. Min Act: -0.0000

Data Index: 1528837 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.1774. Min Act: -0.0000

Data Index: 308367 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 5.6812. Min Range: -5.6812

Max Act: 4.7580. Min Act: -0.0000

Data Index: 1933729 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.1406. Min Act: -0.0000

Data Index: 1904605 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.3297. Min Act: -0.0000

Data Index: 1172414 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.3105. Min Act: -0.0000

Data Index: 1556613 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.0921. Min Act: -0.0000

Data Index: 679983 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 5.6812. Min Range: -5.6812

Max Act: 4.8887. Min Act: -0.0000

Data Index: 1039452 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.4927. Min Act: -0.0000

Data Index: 1593434 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 5.6812. Min Range: -5.6812

Max Act: 4.8868. Min Act: -0.0000

Data Index: 746728 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.2152. Min Act: -0.0000

Data Index: 760707 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.2395. Min Act: -0.0000

Data Index: 624755 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.1224. Min Act: -0.0000

Data Index: 1856425 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 5.6812. Min Range: -5.6812

Max Act: 4.8990. Min Act: -0.0000

Data Index: 129359 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 5.6812. Min Range: -5.6812

Max Act: 4.8915. Min Act: -0.0000

Data Index: 77908 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.0661. Min Act: -0.0000

Data Index: 484866 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 5.6812. Min Range: -5.6812

Max Act: 5.0820. Min Act: -0.0000

Data Index: 1594722 (The Pile)

Max Activating Token Index: 447