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

Dataset: The Pile

Neuron 937 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7472. Min Act: -0.0000

Data Index: 471726 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7173. Min Act: -0.0000

Data Index: 179714 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7151. Min Act: -0.0000

Data Index: 860904 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6218. Min Act: -0.0000

Data Index: 930560 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1245608 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1867605 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6139. Min Act: -0.0000

Data Index: 656669 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1033488 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6199. Min Act: -0.0000

Data Index: 860460 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6884. Min Act: -0.0000

Data Index: 411620 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1834418 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1089720 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1658699 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1843673 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1090676 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6054. Min Act: -0.0000

Data Index: 798186 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1460181 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1219437 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5527. Min Act: -0.0000

Data Index: 945103 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5700. Min Act: -0.0000

Data Index: 687664 (The Pile)

Max Activating Token Index: 256