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

Dataset: The Pile

Neuron 2031 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1507682 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.4381. Min Act: -0.0000

Data Index: 673121 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.2525. Min Act: -0.0000

Data Index: 142301 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1112823 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1666 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1478. Min Act: -0.0000

Data Index: 536211 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1631958 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1479. Min Act: -0.0000

Data Index: 469721 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1111. Min Act: -0.0000

Data Index: 478063 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1099225 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0755. Min Act: -0.0000

Data Index: 622374 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0633. Min Act: -0.0000

Data Index: 175761 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1701435 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0879. Min Act: -0.0000

Data Index: 498792 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 1.4381. Min Range: -1.4381

Max Act: 0.9706. Min Act: -0.0000

Data Index: 658664 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1226828 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.4381. Min Range: -1.4381

Max Act: 0.9857. Min Act: -0.0000

Data Index: 24951 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1199154 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 1.4381. Min Range: -1.4381

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1140722 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1120331 (The Pile)

Max Activating Token Index: 160