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

Dataset: The Pile

Neuron 1840 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.3070. Min Act: -0.0000

Data Index: 489724 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.3156. Min Act: 0.0000

Data Index: 430928 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2997. Min Act: -0.0000

Data Index: 967286 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.3103. Min Act: 0.0000

Data Index: 1999072 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.3085. Min Act: 0.0000

Data Index: 1019352 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1724834 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1770469 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2954. Min Act: 0.0000

Data Index: 1752702 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1935732 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2840. Min Act: 0.0000

Data Index: 1382702 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2726. Min Act: -0.0000

Data Index: 267326 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1056088 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2692. Min Act: 0.0000

Data Index: 482329 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1752568 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1851579 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2946. Min Act: 0.0000

Data Index: 1660165 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2693. Min Act: -0.0000

Data Index: 756637 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2625. Min Act: 0.0000

Data Index: 570196 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1845930 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2629. Min Act: 0.0000

Data Index: 390458 (The Pile)

Max Activating Token Index: 806