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

Dataset: The Pile

Neuron 3852 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6829. Min Act: -0.0000

Data Index: 5001 (The Pile)

Max Activating Token Index: 777

Text #1

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.7177. Min Act: -0.0000

Data Index: 721767 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.7337. Min Act: -0.0000

Data Index: 967688 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1727707 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1146181 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1873083 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5965. Min Act: -0.0000

Data Index: 266326 (The Pile)

Max Activating Token Index: 679

Text #7

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1878522 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1930471 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5673. Min Act: -0.0000

Data Index: 758149 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1442715 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5678. Min Act: -0.0000

Data Index: 201078 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5823. Min Act: -0.0000

Data Index: 755157 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1625867 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1739029 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1028017 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6204. Min Act: -0.0000

Data Index: 723115 (The Pile)

Max Activating Token Index: 628

Text #17

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1130395 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5964. Min Act: -0.0000

Data Index: 730292 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1152330 (The Pile)

Max Activating Token Index: 449