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

Dataset: The Pile

Neuron 4834 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.4360. Min Act: -0.0000

Data Index: 135004 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1121298 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1220295 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1721455 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0754. Min Act: -0.0000

Data Index: 482522 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1024741 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.9754. Min Act: -0.0000

Data Index: 436709 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1721205 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1072285 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1330719 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.8782. Min Act: -0.0000

Data Index: 710874 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1036228 (The Pile)

Max Activating Token Index: 739

Text #12

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.8036. Min Act: -0.0000

Data Index: 760100 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.7863. Min Act: -0.0000

Data Index: 607592 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.8237. Min Act: -0.0000

Data Index: 444127 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1756923 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.7678. Min Act: -0.0000

Data Index: 883725 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.7897. Min Act: -0.0000

Data Index: 122689 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1442499 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.7633. Min Act: -0.0000

Data Index: 360978 (The Pile)

Max Activating Token Index: 241