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

Dataset: The Pile

Neuron 3316 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: 0.4927. Min Range: -0.4927

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1171684 (The Pile)

Max Activating Token Index: 212

Text #1

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4712. Min Act: -0.0000

Data Index: 355527 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4348. Min Act: -0.0000

Data Index: 420190 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4000. Min Act: -0.0000

Data Index: 931086 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3602. Min Act: -0.0000

Data Index: 451956 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3733. Min Act: -0.0000

Data Index: 156598 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3821. Min Act: -0.0000

Data Index: 277557 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1852695 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1916037 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3694. Min Act: -0.0000

Data Index: 86676 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3941. Min Act: -0.0000

Data Index: 843439 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1498201 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1161465 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3486. Min Act: -0.0000

Data Index: 372789 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1986009 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3398. Min Act: -0.0000

Data Index: 100772 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3586. Min Act: -0.0000

Data Index: 506731 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3664. Min Act: -0.0000

Data Index: 890763 (The Pile)

Max Activating Token Index: 292

Text #18

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3428. Min Act: -0.0000

Data Index: 616149 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3427. Min Act: -0.0000

Data Index: 5087 (The Pile)

Max Activating Token Index: 584