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

Dataset: The Pile

Neuron 588 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: 0.7773. Min Range: -0.7773

Max Act: 0.7773. Min Act: -0.0000

Data Index: 544612 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1654613 (The Pile)

Max Activating Token Index: 344

Text #2

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1437903 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7373. Min Act: -0.0000

Data Index: 647562 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7037. Min Act: 0.0000

Data Index: 263946 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6978. Min Act: -0.0000

Data Index: 427623 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6968. Min Act: -0.0000

Data Index: 872821 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1026837 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6893. Min Act: -0.0000

Data Index: 510506 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1338197 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.5943. Min Act: -0.0000

Data Index: 536294 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1078872 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1124440 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.5898. Min Act: -0.0000

Data Index: 821452 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1346379 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6198. Min Act: -0.0000

Data Index: 258729 (The Pile)

Max Activating Token Index: 413

Text #16

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1089052 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1257808 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.5898. Min Act: -0.0000

Data Index: 795061 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.5247. Min Act: -0.0000

Data Index: 55289 (The Pile)

Max Activating Token Index: 534