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

Dataset: The Pile

Neuron 617 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: 1.1596. Min Range: -1.1596

Max Act: 1.1596. Min Act: -0.0000

Data Index: 439858 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1473. Min Act: -0.0000

Data Index: 985950 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0001. Min Act: -0.0000

Data Index: 535093 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9220. Min Act: -0.0000

Data Index: 845756 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1413077 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1989867 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9750. Min Act: -0.0000

Data Index: 789855 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9620. Min Act: -0.0000

Data Index: 976197 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9488. Min Act: -0.0000

Data Index: 524715 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1914101 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0054. Min Act: -0.0000

Data Index: 588285 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8158. Min Act: 0.0000

Data Index: 215066 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8457. Min Act: -0.0000

Data Index: 726991 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1838498 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1370778 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9110. Min Act: -0.0000

Data Index: 264437 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1333957 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9231. Min Act: -0.0000

Data Index: 753443 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9469. Min Act: -0.0000

Data Index: 615378 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1579593 (The Pile)

Max Activating Token Index: 70