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

Dataset: The Pile

Neuron 3617 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: 0.5769. Min Range: -0.5769

Max Act: 0.5335. Min Act: -0.0000

Data Index: 18529 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1109963 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1602909 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5063. Min Act: -0.0000

Data Index: 864454 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5480. Min Act: -0.0000

Data Index: 360300 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5134. Min Act: -0.0000

Data Index: 496783 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1941858 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4796. Min Act: -0.0000

Data Index: 560574 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4798. Min Act: -0.0000

Data Index: 874878 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1460566 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4472. Min Act: -0.0000

Data Index: 548666 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4556. Min Act: -0.0000

Data Index: 586321 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4659. Min Act: -0.0000

Data Index: 579710 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1610060 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1917738 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4744. Min Act: -0.0000

Data Index: 627177 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5224. Min Act: -0.0000

Data Index: 497593 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1622137 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1247429 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4597. Min Act: -0.0000

Data Index: 677951 (The Pile)

Max Activating Token Index: 494