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

Dataset: The Pile

Neuron 3280 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: 1.6908. Min Range: -1.6908

Max Act: 1.5901. Min Act: -0.0000

Data Index: 1154202 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.6908. Min Act: -0.0000

Data Index: 544683 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.5714. Min Act: -0.0000

Data Index: 690387 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.4659. Min Act: -0.0000

Data Index: 740853 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.5358. Min Act: -0.0000

Data Index: 837882 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.4893. Min Act: -0.0000

Data Index: 1706040 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3725. Min Act: -0.0000

Data Index: 574699 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.4113. Min Act: -0.0000

Data Index: 1744996 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1454097 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.2286. Min Act: -0.0000

Data Index: 557556 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.2000. Min Act: -0.0000

Data Index: 792815 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1969284 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3264. Min Act: -0.0000

Data Index: 816367 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3095. Min Act: -0.0000

Data Index: 1682831 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1382145 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3202. Min Act: -0.0000

Data Index: 684666 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.2537. Min Act: -0.0000

Data Index: 512947 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1616031 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.1693. Min Act: -0.0000

Data Index: 47388 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.2925. Min Act: -0.0000

Data Index: 261002 (The Pile)

Max Activating Token Index: 1005