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

Dataset: The Pile

Neuron 550 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: 1.6511. Min Range: -1.6511

Max Act: 1.6511. Min Act: -0.0000

Data Index: 962405 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.4925. Min Act: -0.0000

Data Index: 346372 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.5518. Min Act: -0.0000

Data Index: 1584561 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1399837 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1868126 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.4346. Min Act: -0.0000

Data Index: 1125214 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2046. Min Act: -0.0000

Data Index: 384998 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1135494 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1739766 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2194. Min Act: -0.0000

Data Index: 351032 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1782575 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 1.6511. Min Range: -1.6511

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1144537 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.1414. Min Act: -0.0000

Data Index: 903204 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1434700 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.0615. Min Act: -0.0000

Data Index: 702491 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.1736. Min Act: -0.0000

Data Index: 181514 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.1079. Min Act: -0.0000

Data Index: 373993 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.1612. Min Act: -0.0000

Data Index: 454652 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.1522. Min Act: -0.0000

Data Index: 464494 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1799376 (The Pile)

Max Activating Token Index: 739