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

Dataset: The Pile

Neuron 805 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: 1.2630. Min Range: -1.2630

Max Act: 1.2630. Min Act: -0.0000

Data Index: 627602 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.0587. Min Act: -0.0000

Data Index: 928631 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.0607. Min Act: -0.0000

Data Index: 696739 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.1051. Min Act: -0.0000

Data Index: 661546 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.1265. Min Act: -0.0000

Data Index: 475042 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.0584. Min Act: -0.0000

Data Index: 430183 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1759406 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9793. Min Act: -0.0000

Data Index: 645292 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1485459 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1617356 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9911. Min Act: 0.0000

Data Index: 1597152 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1279609 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7954. Min Act: -0.0000

Data Index: 457893 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1986047 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1198237 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1928462 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9246. Min Act: -0.0000

Data Index: 242533 (The Pile)

Max Activating Token Index: 460

Text #17

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9262. Min Act: -0.0000

Data Index: 378389 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1032754 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1126821 (The Pile)

Max Activating Token Index: 735