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

Dataset: The Pile

Neuron 2213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.7360. Min Act: -0.0000

Data Index: 766109 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6581. Min Act: -0.0000

Data Index: 551193 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6049. Min Act: -0.0000

Data Index: 177282 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1848155 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1775403 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5594. Min Act: -0.0000

Data Index: 178593 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6176. Min Act: -0.0000

Data Index: 493600 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5896. Min Act: -0.0000

Data Index: 518562 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5871. Min Act: -0.0000

Data Index: 773186 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5294. Min Act: -0.0000

Data Index: 586674 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1272372 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1989094 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1276850 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1460218 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6080. Min Act: -0.0000

Data Index: 282851 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5615. Min Act: -0.0000

Data Index: 737663 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1204790 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5223. Min Act: -0.0000

Data Index: 342866 (The Pile)

Max Activating Token Index: 765

Text #18

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5335. Min Act: -0.0000

Data Index: 513080 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1794944 (The Pile)

Max Activating Token Index: 17