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

Dataset: The Pile

Neuron 3989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1338604 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.4422. Min Act: -0.0000

Data Index: 970157 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.5362. Min Act: -0.0000

Data Index: 497107 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1030352 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3140. Min Act: -0.0000

Data Index: 829060 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3026. Min Act: -0.0000

Data Index: 201106 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3527. Min Act: -0.0000

Data Index: 1739740 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2597. Min Act: -0.0000

Data Index: 566587 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1111069 (The Pile)

Max Activating Token Index: 565

Text #9

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1482. Min Act: -0.0000

Data Index: 1799603 (The Pile)

Max Activating Token Index: 867

Text #10

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1382415 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2843. Min Act: -0.0000

Data Index: 573932 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1922. Min Act: -0.0000

Data Index: 177568 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2581. Min Act: -0.0000

Data Index: 690793 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1140. Min Act: -0.0000

Data Index: 196157 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.0519. Min Act: -0.0000

Data Index: 972219 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2369. Min Act: -0.0000

Data Index: 204972 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1576198 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1063556 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1720722 (The Pile)

Max Activating Token Index: 420