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

Dataset: The Pile

Neuron 4333 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: 0.8025. Min Range: -0.8025

Max Act: 0.7744. Min Act: -0.0000

Data Index: 285437 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1492490 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.8025. Min Act: -0.0000

Data Index: 830919 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7536. Min Act: -0.0000

Data Index: 690653 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1555679 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.6901. Min Act: -0.0000

Data Index: 530686 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.6012. Min Act: -0.0000

Data Index: 200129 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1152771 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5555. Min Act: -0.0000

Data Index: 834956 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1961131 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1276455 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5689. Min Act: -0.0000

Data Index: 401610 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5725. Min Act: -0.0000

Data Index: 704830 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1149419 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5153. Min Act: -0.0000

Data Index: 638205 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1646480 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1026924 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1760636 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1425041 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1972275 (The Pile)

Max Activating Token Index: 514