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

Dataset: The Pile

Neuron 2775 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: 0.5932. Min Range: -0.5932

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1947406 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1833880 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5932. Min Act: -0.0000

Data Index: 98548 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5335. Min Act: -0.0000

Data Index: 943492 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4981. Min Act: -0.0000

Data Index: 588829 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4782. Min Act: -0.0000

Data Index: 822250 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5115. Min Act: -0.0000

Data Index: 252476 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1965635 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4706. Min Act: -0.0000

Data Index: 355542 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4890. Min Act: -0.0000

Data Index: 245727 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4442. Min Act: -0.0000

Data Index: 828067 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4600. Min Act: -0.0000

Data Index: 132623 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1353403 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4531. Min Act: -0.0000

Data Index: 596608 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4669. Min Act: -0.0000

Data Index: 48311 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4793. Min Act: -0.0000

Data Index: 298450 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4894. Min Act: -0.0000

Data Index: 990220 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1615262 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1178164 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4307. Min Act: -0.0000

Data Index: 33164 (The Pile)

Max Activating Token Index: 774