Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 5 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1795624 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1488889 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8829. Min Act: -0.0000

Data Index: 25657 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8194. Min Act: -0.0000

Data Index: 106042 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1526113 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7415. Min Act: -0.0000

Data Index: 430263 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1129037 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1355847 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7802. Min Act: -0.0000

Data Index: 143976 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7634. Min Act: -0.0000

Data Index: 113596 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1839018 (The Pile)

Max Activating Token Index: 797

Text #11

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1773971 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1942461 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1658282 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6683. Min Act: -0.0000

Data Index: 225802 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1127721 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1629071 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1773729 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1822609 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1357280 (The Pile)

Max Activating Token Index: 321