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

Dataset: The Pile

Neuron 1837 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0813. Min Range: -1.0813

Max Act: 1.0813. Min Act: -0.0000

Data Index: 431805 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.9670. Min Act: -0.0000

Data Index: 243306 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.8398. Min Act: -0.0000

Data Index: 718497 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1717686 (The Pile)

Max Activating Token Index: 346

Text #4

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.9409. Min Act: -0.0000

Data Index: 227748 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1449366 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7802. Min Act: -0.0000

Data Index: 387700 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7215. Min Act: -0.0000

Data Index: 342882 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7518. Min Act: -0.0000

Data Index: 391330 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.8629. Min Act: -0.0000

Data Index: 661208 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7468. Min Act: -0.0000

Data Index: 912455 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1049060 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7241. Min Act: -0.0000

Data Index: 510515 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1353542 (The Pile)

Max Activating Token Index: 56

Text #14

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1194272 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7624. Min Act: -0.0000

Data Index: 656248 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7157. Min Act: 0.0000

Data Index: 644317 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1155980 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1572400 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6667. Min Act: -0.0000

Data Index: 111481 (The Pile)

Max Activating Token Index: 396