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

Dataset: The Pile

Neuron 3563 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: 0.8949. Min Range: -0.8949

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1435893 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7807. Min Act: -0.0000

Data Index: 743031 (The Pile)

Max Activating Token Index: 711

Text #2

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1693961 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7796. Min Act: -0.0000

Data Index: 631216 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1520294 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1533856 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1857855 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7189. Min Act: -0.0000

Data Index: 986242 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7242. Min Act: -0.0000

Data Index: 534169 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1898370 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1810855 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7075. Min Act: -0.0000

Data Index: 483099 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1167439 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1932053 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1612739 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1110817 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.6580. Min Act: -0.0000

Data Index: 743589 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7044. Min Act: -0.0000

Data Index: 847725 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7070. Min Act: -0.0000

Data Index: 400814 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7143. Min Act: -0.0000

Data Index: 947979 (The Pile)

Max Activating Token Index: 45