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

Dataset: The Pile

Neuron 1116 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0378. Min Range: -1.0378

Max Act: 1.0378. Min Act: -0.0000

Data Index: 738191 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1953587 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9030. Min Act: -0.0000

Data Index: 245635 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1224311 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9102. Min Act: -0.0000

Data Index: 1040789 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9000. Min Act: -0.0000

Data Index: 542309 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8813. Min Act: -0.0000

Data Index: 388796 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1076461 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9279. Min Act: -0.0000

Data Index: 601947 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8972. Min Act: -0.0000

Data Index: 467821 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1477334 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8395. Min Act: -0.0000

Data Index: 406449 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8363. Min Act: -0.0000

Data Index: 11249 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8106. Min Act: -0.0000

Data Index: 76247 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1487190 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8306. Min Act: -0.0000

Data Index: 518157 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1691735 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1391985 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1656765 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1190373 (The Pile)

Max Activating Token Index: 651