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

Dataset: The Pile

Neuron 3745 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.7151. Min Act: -0.0000

Data Index: 651902 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1883454 (The Pile)

Max Activating Token Index: 359

Text #2

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1669916 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.6046. Min Act: -0.0000

Data Index: 289183 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5611. Min Act: -0.0000

Data Index: 488221 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5756. Min Act: -0.0000

Data Index: 272628 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1431435 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1598045 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1631795 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1987271 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5727. Min Act: -0.0000

Data Index: 646474 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5435. Min Act: -0.0000

Data Index: 22558 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5525. Min Act: -0.0000

Data Index: 177735 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1130936 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1266474 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1419445 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.4695. Min Act: -0.0000

Data Index: 895172 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1290590 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.4486. Min Act: -0.0000

Data Index: 220383 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5302. Min Act: -0.0000

Data Index: 98370 (The Pile)

Max Activating Token Index: 889