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

Dataset: The Pile

Neuron 3845 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1672300 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1823014 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7434. Min Act: -0.0000

Data Index: 610318 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7208. Min Act: -0.0000

Data Index: 168029 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1501924 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5134. Min Act: -0.0000

Data Index: 47114 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1740358 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5246. Min Act: -0.0000

Data Index: 919492 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5670. Min Act: -0.0000

Data Index: 91424 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1885879 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5163. Min Act: -0.0000

Data Index: 593431 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5344. Min Act: 0.0000

Data Index: 597790 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.4392. Min Act: -0.0000

Data Index: 695920 (The Pile)

Max Activating Token Index: 871

Text #13

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1061968 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5468. Min Act: -0.0000

Data Index: 549766 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1350985 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1373248 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5013. Min Act: -0.0000

Data Index: 319945 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1358574 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5277. Min Act: 0.0000

Data Index: 1802791 (The Pile)

Max Activating Token Index: 748