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

Dataset: The Pile

Neuron 505 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.8110. Min Act: -0.0000

Data Index: 454495 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7351. Min Act: -0.0000

Data Index: 344594 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7495. Min Act: -0.0000

Data Index: 279103 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7494. Min Act: -0.0000

Data Index: 479460 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6236. Min Act: -0.0000

Data Index: 821755 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7004. Min Act: -0.0000

Data Index: 515106 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6638. Min Act: -0.0000

Data Index: 769173 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6467. Min Act: -0.0000

Data Index: 1732291 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6960. Min Act: -0.0000

Data Index: 1107450 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1576647 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6225. Min Act: -0.0000

Data Index: 1505125 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7062. Min Act: -0.0000

Data Index: 1612543 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6351. Min Act: -0.0000

Data Index: 791207 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5911. Min Act: -0.0000

Data Index: 70493 (The Pile)

Max Activating Token Index: 997

Text #14

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5870. Min Act: -0.0000

Data Index: 827343 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6722. Min Act: -0.0000

Data Index: 1921656 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6547. Min Act: -0.0000

Data Index: 230542 (The Pile)

Max Activating Token Index: 980

Text #17

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6612. Min Act: -0.0000

Data Index: 1595422 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5484. Min Act: -0.0000

Data Index: 1873099 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5901. Min Act: -0.0000

Data Index: 102397 (The Pile)

Max Activating Token Index: 239