Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 443 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1966444 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0096. Min Act: -0.0000

Data Index: 430426 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.2043. Min Act: -0.0000

Data Index: 704177 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.1459. Min Act: -0.0000

Data Index: 681944 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1964876 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1492344 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0443. Min Act: -0.0000

Data Index: 795302 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.1155. Min Act: -0.0000

Data Index: 167863 (The Pile)

Max Activating Token Index: 744

Text #8

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0305. Min Act: -0.0000

Data Index: 390060 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0443. Min Act: -0.0000

Data Index: 443592 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0627. Min Act: -0.0000

Data Index: 766214 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1705653 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0736. Min Act: -0.0000

Data Index: 394613 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1288660 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1737394 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1063338 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0361. Min Act: -0.0000

Data Index: 634187 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1600295 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1229962 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1011442 (The Pile)

Max Activating Token Index: 473