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

Dataset: The Pile

Neuron 546 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: 0.8687. Min Range: -0.8687

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1470974 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6677. Min Act: -0.0000

Data Index: 531456 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1749578 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6591. Min Act: 0.0000

Data Index: 956834 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1028046 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1458466 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1691754 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6064. Min Act: -0.0000

Data Index: 409736 (The Pile)

Max Activating Token Index: 287

Text #8

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5868. Min Act: -0.0000

Data Index: 287223 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1377172 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1214772 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5693. Min Act: -0.0000

Data Index: 507864 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6105. Min Act: -0.0000

Data Index: 746617 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1764219 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1915543 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5749. Min Act: -0.0000

Data Index: 756988 (The Pile)

Max Activating Token Index: 593

Text #16

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1714722 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1935733 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1528317 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1030883 (The Pile)

Max Activating Token Index: 736