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

Dataset: The Pile

Neuron 3096 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: 0.7025. Min Range: -0.7025

Max Act: 0.7025. Min Act: -0.0000

Data Index: 549391 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.6194. Min Act: -0.0000

Data Index: 130856 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1241432 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1461933 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5772. Min Act: -0.0000

Data Index: 92478 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1034106 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1389194 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1764675 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5207. Min Act: -0.0000

Data Index: 437184 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5038. Min Act: -0.0000

Data Index: 826814 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1002572 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4783. Min Act: -0.0000

Data Index: 271693 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1656992 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1797354 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4122. Min Act: -0.0000

Data Index: 111852 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.3935. Min Act: -0.0000

Data Index: 648842 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4117. Min Act: -0.0000

Data Index: 778700 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.3979. Min Act: -0.0000

Data Index: 780430 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.3484. Min Act: 0.0000

Data Index: 1894694 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1516540 (The Pile)

Max Activating Token Index: 235