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

Dataset: The Pile

Neuron 3657 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1766457 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.1855. Min Act: -0.0000

Data Index: 487948 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.1502. Min Act: -0.0000

Data Index: 1261798 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.0152. Min Act: -0.0000

Data Index: 874038 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9238. Min Act: -0.0000

Data Index: 220678 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 1.1910. Min Range: -1.1910

Max Act: 1.0725. Min Act: -0.0000

Data Index: 68531 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.8683. Min Act: -0.0000

Data Index: 180722 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9118. Min Act: -0.0000

Data Index: 271788 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7955. Min Act: 0.0000

Data Index: 733436 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.9006. Min Act: -0.0000

Data Index: 378450 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7766. Min Act: -0.0000

Data Index: 551699 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1539139 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1381682 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7721. Min Act: -0.0000

Data Index: 440105 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1690417 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7592. Min Act: -0.0000

Data Index: 521832 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7923. Min Act: -0.0000

Data Index: 643054 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7545. Min Act: -0.0000

Data Index: 779235 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7946. Min Act: -0.0000

Data Index: 809097 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 1.1910. Min Range: -1.1910

Max Act: 0.7750. Min Act: -0.0000

Data Index: 595353 (The Pile)

Max Activating Token Index: 210