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

Dataset: The Pile

Neuron 4594 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: 0.8877. Min Range: -0.8877

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1380408 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7713. Min Act: -0.0000

Data Index: 255118 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6684. Min Act: -0.0000

Data Index: 867368 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6723. Min Act: -0.0000

Data Index: 523119 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6522. Min Act: -0.0000

Data Index: 990858 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1903994 (The Pile)

Max Activating Token Index: 788

Text #6

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1074450 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6247. Min Act: -0.0000

Data Index: 843868 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5390. Min Act: -0.0000

Data Index: 285565 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6308. Min Act: -0.0000

Data Index: 700774 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1938989 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1988417 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1870567 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1708759 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1053210 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6081. Min Act: -0.0000

Data Index: 207386 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5344. Min Act: -0.0000

Data Index: 158364 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1761686 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5413. Min Act: -0.0000

Data Index: 624848 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5638. Min Act: -0.0000

Data Index: 95987 (The Pile)

Max Activating Token Index: 715