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

Dataset: The Pile

Neuron 4768 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: 1.5438. Min Range: -1.5438

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1972911 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4358. Min Act: -0.0000

Data Index: 185271 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4109. Min Act: -0.0000

Data Index: 439171 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2757. Min Act: -0.0000

Data Index: 622060 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3470. Min Act: -0.0000

Data Index: 955957 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1727917 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3053. Min Act: -0.0000

Data Index: 706566 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2601. Min Act: 0.0000

Data Index: 639400 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2606. Min Act: -0.0000

Data Index: 295915 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2590. Min Act: -0.0000

Data Index: 214427 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2458. Min Act: -0.0000

Data Index: 692586 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2259. Min Act: -0.0000

Data Index: 839895 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1690767 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2729. Min Act: -0.0000

Data Index: 770217 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2374. Min Act: -0.0000

Data Index: 988420 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.1888. Min Act: -0.0000

Data Index: 47574 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1995020 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.1746. Min Act: -0.0000

Data Index: 543010 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1056796 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1236368 (The Pile)

Max Activating Token Index: 426