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

Dataset: The Pile

Neuron 2254 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: 1.2975. Min Range: -1.2975

Max Act: 1.2975. Min Act: -0.0000

Data Index: 974065 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.2054. Min Act: -0.0000

Data Index: 848532 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.1283. Min Act: -0.0000

Data Index: 180152 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.2703. Min Act: -0.0000

Data Index: 261497 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.2952. Min Act: -0.0000

Data Index: 496628 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1995356 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0795. Min Act: -0.0000

Data Index: 773564 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.1204. Min Act: -0.0000

Data Index: 752383 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1609011 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9492. Min Act: -0.0000

Data Index: 912659 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1042550 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1572671 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1315095 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1698785 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1474703 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0052. Min Act: -0.0000

Data Index: 144001 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1885452 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9859. Min Act: -0.0000

Data Index: 989405 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1212409 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9462. Min Act: -0.0000

Data Index: 627568 (The Pile)

Max Activating Token Index: 235