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

Dataset: The Pile

Neuron 1899 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: 3.3986. Min Range: -3.3986

Max Act: 3.3986. Min Act: -0.0000

Data Index: 420022 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.3729. Min Act: -0.0000

Data Index: 15571 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.0906. Min Act: -0.0000

Data Index: 1693891 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.9759. Min Act: -0.0000

Data Index: 1291664 (The Pile)

Max Activating Token Index: 889

Text #4

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.0992. Min Act: -0.0000

Data Index: 873215 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.0733. Min Act: 0.0000

Data Index: 132781 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.0389. Min Act: -0.0000

Data Index: 1210736 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.1461. Min Act: -0.0000

Data Index: 383640 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.9588. Min Act: -0.0000

Data Index: 1881036 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.9848. Min Act: -0.0000

Data Index: 1281628 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.6786. Min Act: -0.0000

Data Index: 264263 (The Pile)

Max Activating Token Index: 975

Text #11

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.7780. Min Act: -0.0000

Data Index: 644048 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.9302. Min Act: -0.0000

Data Index: 47258 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.8868. Min Act: -0.0000

Data Index: 1824563 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.0397. Min Act: -0.0000

Data Index: 251002 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.8756. Min Act: -0.0000

Data Index: 800167 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.8693. Min Act: -0.0000

Data Index: 239164 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.8381. Min Act: -0.0000

Data Index: 1760100 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 3.3986. Min Range: -3.3986

Max Act: 2.8395. Min Act: -0.0000

Data Index: 1478511 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 3.3986. Min Range: -3.3986

Max Act: 3.1184. Min Act: -0.0000

Data Index: 1446007 (The Pile)

Max Activating Token Index: 616