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

Dataset: The Pile

Neuron 4521 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: 1.5477. Min Range: -1.5477

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1227343 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1718014 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1583360 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.5477. Min Act: -0.0000

Data Index: 594709 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1760167 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1981270 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1639. Min Act: -0.0000

Data Index: 24549 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.2748. Min Act: -0.0000

Data Index: 397988 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1158211 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1351006 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1745827 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1620165 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1361. Min Act: -0.0000

Data Index: 942824 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1198. Min Act: -0.0000

Data Index: 78877 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1118. Min Act: -0.0000

Data Index: 834954 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1673968 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1591. Min Act: -0.0000

Data Index: 548987 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1802231 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.0602. Min Act: -0.0000

Data Index: 531585 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 1.5477. Min Range: -1.5477

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1789718 (The Pile)

Max Activating Token Index: 846