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

Dataset: The Pile

Neuron 3910 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.8688. Min Act: -0.0000

Data Index: 766953 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6870. Min Act: -0.0000

Data Index: 414946 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6333. Min Act: -0.0000

Data Index: 765588 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1531370 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6804. Min Act: -0.0000

Data Index: 802633 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6787. Min Act: -0.0000

Data Index: 98699 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6737. Min Act: -0.0000

Data Index: 749985 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6248. Min Act: -0.0000

Data Index: 854695 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1029173 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1227836 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1180550 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6373. Min Act: -0.0000

Data Index: 502529 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6313. Min Act: -0.0000

Data Index: 405498 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6288. Min Act: -0.0000

Data Index: 661200 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1732662 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1983471 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6190. Min Act: -0.0000

Data Index: 424520 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1152026 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1201787 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1052940 (The Pile)

Max Activating Token Index: 39