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

Dataset: The Pile

Neuron 8 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: 0.6187. Min Range: -0.6187

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1048130 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5281. Min Act: -0.0000

Data Index: 383626 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1461190 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1871089 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5168. Min Act: -0.0000

Data Index: 493165 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4845. Min Act: -0.0000

Data Index: 469983 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5072. Min Act: -0.0000

Data Index: 602392 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4805. Min Act: -0.0000

Data Index: 122554 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1481864 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4619. Min Act: -0.0000

Data Index: 563000 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1408549 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4520. Min Act: -0.0000

Data Index: 962046 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4371. Min Act: -0.0000

Data Index: 86199 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4468. Min Act: -0.0000

Data Index: 290604 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1773354 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4289. Min Act: -0.0000

Data Index: 619398 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1690150 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4533. Min Act: -0.0000

Data Index: 929868 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1942932 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1609389 (The Pile)

Max Activating Token Index: 350