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

Dataset: The Pile

Neuron 3128 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.7098. Min Act: -0.0000

Data Index: 240800 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.6152. Min Act: -0.0000

Data Index: 83953 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.6764. Min Act: -0.0000

Data Index: 764575 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1634720 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1767660 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1399666 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.6077. Min Act: -0.0000

Data Index: 350259 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5779. Min Act: -0.0000

Data Index: 799698 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5392. Min Act: -0.0000

Data Index: 992284 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1369131 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1086419 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.6018. Min Act: -0.0000

Data Index: 857973 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1505285 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1916916 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1686250 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1574302 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1635180 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1088391 (The Pile)

Max Activating Token Index: 27

Text #18

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1884551 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 0.7098. Min Range: -0.7098

Max Act: 0.5783. Min Act: -0.0000

Data Index: 998517 (The Pile)

Max Activating Token Index: 709