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

Dataset: The Pile

Neuron 4002 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.8791. Min Act: -0.0000

Data Index: 186334 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.8082. Min Act: -0.0000

Data Index: 191655 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.9225. Min Act: -0.0000

Data Index: 1239476 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.6430. Min Act: -0.0000

Data Index: 152784 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1928576 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.5278. Min Act: -0.0000

Data Index: 142626 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.5990. Min Act: -0.0000

Data Index: 897648 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1475170 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.5537. Min Act: -0.0000

Data Index: 627312 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1981515 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.5268. Min Act: -0.0000

Data Index: 1023260 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4906. Min Act: -0.0000

Data Index: 162075 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.3207. Min Act: -0.0000

Data Index: 761793 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4659. Min Act: -0.0000

Data Index: 909119 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4437. Min Act: -0.0000

Data Index: 273021 (The Pile)

Max Activating Token Index: 185

Text #15

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4248. Min Act: -0.0000

Data Index: 318254 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1706096 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1653444 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1776300 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 1.9225. Min Range: -1.9225

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1603018 (The Pile)

Max Activating Token Index: 465