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

Dataset: The Pile

Neuron 4625 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: 1.8158. Min Range: -1.8158

Max Act: 1.8158. Min Act: -0.0000

Data Index: 1131426 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.7362. Min Act: -0.0000

Data Index: 1875255 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.5043. Min Act: -0.0000

Data Index: 522701 (The Pile)

Max Activating Token Index: 678

Text #3

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1650670 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1548928 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.5754. Min Act: -0.0000

Data Index: 469041 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1753230 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.3598. Min Act: -0.0000

Data Index: 322916 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1434746 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1834960 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.3976. Min Act: -0.0000

Data Index: 385276 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1347708 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.3513. Min Act: -0.0000

Data Index: 1709881 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1564385 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.0948. Min Act: -0.0000

Data Index: 643867 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.1769. Min Act: -0.0000

Data Index: 1874290 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1148549 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1556406 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1011671 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 1.8158. Min Range: -1.8158

Max Act: 1.0276. Min Act: -0.0000

Data Index: 309419 (The Pile)

Max Activating Token Index: 947