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

Dataset: The Pile

Neuron 3967 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: 1.0706. Min Range: -1.0706

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1010777 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.8719. Min Act: -0.0000

Data Index: 466000 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1540407 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.8698. Min Act: -0.0000

Data Index: 691865 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1427670 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1442017 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9023. Min Act: -0.0000

Data Index: 105330 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.8321. Min Act: -0.0000

Data Index: 880433 (The Pile)

Max Activating Token Index: 246

Text #8

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1669352 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7661. Min Act: -0.0000

Data Index: 299856 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1737105 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7823. Min Act: -0.0000

Data Index: 192213 (The Pile)

Max Activating Token Index: 972

Text #12

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1696073 (The Pile)

Max Activating Token Index: 495

Text #13

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1241868 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7759. Min Act: -0.0000

Data Index: 359869 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1971700 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.6987. Min Act: -0.0000

Data Index: 341643 (The Pile)

Max Activating Token Index: 836

Text #17

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7550. Min Act: -0.0000

Data Index: 677854 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.7685. Min Act: -0.0000

Data Index: 390200 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.0706. Min Range: -1.0706

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1058756 (The Pile)

Max Activating Token Index: 787