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

Dataset: The Pile

Neuron 3666 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: 0.9905. Min Range: -0.9905

Max Act: 0.9905. Min Act: -0.0000

Data Index: 766888 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9213. Min Act: -0.0000

Data Index: 747757 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8606. Min Act: -0.0000

Data Index: 304709 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8098. Min Act: -0.0000

Data Index: 18448 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1587386 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8809. Min Act: -0.0000

Data Index: 980623 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8188. Min Act: -0.0000

Data Index: 275550 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1064305 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1972958 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7730. Min Act: -0.0000

Data Index: 497786 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7723. Min Act: -0.0000

Data Index: 642801 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7722. Min Act: -0.0000

Data Index: 77438 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7228. Min Act: -0.0000

Data Index: 405946 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1059786 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1981072 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7196. Min Act: -0.0000

Data Index: 398990 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1249470 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6589. Min Act: -0.0000

Data Index: 619842 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7183. Min Act: -0.0000

Data Index: 457403 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6664. Min Act: -0.0000

Data Index: 48644 (The Pile)

Max Activating Token Index: 375