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

Dataset: The Pile

Neuron 1852 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.8157. Min Act: -0.0000

Data Index: 567966 (The Pile)

Max Activating Token Index: 371

Text #1

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.8207. Min Act: -0.0000

Data Index: 755411 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7600. Min Act: -0.0000

Data Index: 408919 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7204. Min Act: -0.0000

Data Index: 927051 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1405948 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1170967 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7618. Min Act: -0.0000

Data Index: 642222 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1400957 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6932. Min Act: -0.0000

Data Index: 573816 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1087401 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6219. Min Act: -0.0000

Data Index: 925834 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1595504 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1128947 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6072. Min Act: -0.0000

Data Index: 143660 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1167036 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.5644. Min Act: -0.0000

Data Index: 858127 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.5935. Min Act: -0.0000

Data Index: 905775 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6118. Min Act: -0.0000

Data Index: 403080 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1531033 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 0.8207. Min Range: -0.8207

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1868794 (The Pile)

Max Activating Token Index: 886