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

Dataset: The Pile

Neuron 1704 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: 0.8724. Min Range: -0.8724

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1067974 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8575. Min Act: -0.0000

Data Index: 993510 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8222. Min Act: -0.0000

Data Index: 658972 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8507. Min Act: -0.0000

Data Index: 808680 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7779. Min Act: -0.0000

Data Index: 253378 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1736626 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1056916 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1849768 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1705189 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6903. Min Act: -0.0000

Data Index: 43551 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1628945 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6789. Min Act: -0.0000

Data Index: 396402 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1098230 (The Pile)

Max Activating Token Index: 796

Text #13

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1260745 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6844. Min Act: -0.0000

Data Index: 159445 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6559. Min Act: -0.0000

Data Index: 938312 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1118626 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1778204 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6460. Min Act: -0.0000

Data Index: 976454 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6604. Min Act: -0.0000

Data Index: 123733 (The Pile)

Max Activating Token Index: 887