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

Dataset: The Pile

Neuron 3461 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: 1.2186. Min Range: -1.2186

Max Act: 1.2186. Min Act: -0.0000

Data Index: 490440 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1473368 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1869646 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1444366 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.8649. Min Act: -0.0000

Data Index: 273323 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.8180. Min Act: -0.0000

Data Index: 361724 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.8371. Min Act: -0.0000

Data Index: 789431 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1216979 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.8329. Min Act: 0.0000

Data Index: 1677771 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1066459 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1659973 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.7079. Min Act: -0.0000

Data Index: 710551 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1182239 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.7273. Min Act: -0.0000

Data Index: 807012 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1060654 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.6695. Min Act: -0.0000

Data Index: 147939 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1996179 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1058537 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.6816. Min Act: 0.0000

Data Index: 1188260 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.6765. Min Act: -0.0000

Data Index: 122252 (The Pile)

Max Activating Token Index: 64