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

Dataset: The Pile

Neuron 3417 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: 0.1733. Min Range: -0.1733

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1313538 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1855439 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1118. Min Act: -0.0000

Data Index: 26048 (The Pile)

Max Activating Token Index: 559

Text #3

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1076. Min Act: -0.0000

Data Index: 934701 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1563519 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1150275 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1332021 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0985. Min Act: -0.0000

Data Index: 726700 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1852993 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1575552 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1837707 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1010236 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1732548 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1468453 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0919. Min Act: -0.0000

Data Index: 845767 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1268641 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0913. Min Act: -0.0000

Data Index: 739769 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0746. Min Act: -0.0000

Data Index: 527603 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1765226 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1004397 (The Pile)

Max Activating Token Index: 447