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

Dataset: The Pile

Neuron 3280 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: 0.6467. Min Range: -0.6467

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1236877 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1935555 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.5801. Min Act: -0.0000

Data Index: 107325 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.5167. Min Act: -0.0000

Data Index: 577037 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.5041. Min Act: -0.0000

Data Index: 17547 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1442467 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4860. Min Act: -0.0000

Data Index: 424653 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1923109 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4688. Min Act: -0.0000

Data Index: 566953 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4667. Min Act: -0.0000

Data Index: 57281 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4579. Min Act: -0.0000

Data Index: 478576 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4246. Min Act: -0.0000

Data Index: 843278 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1659821 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4200. Min Act: -0.0000

Data Index: 359493 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4065. Min Act: -0.0000

Data Index: 946785 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4149. Min Act: -0.0000

Data Index: 579289 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1793954 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4320. Min Act: -0.0000

Data Index: 208437 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1943517 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1782156 (The Pile)

Max Activating Token Index: 541