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

Dataset: The Pile

Neuron 4208 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: 0.9150. Min Range: -0.9150

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1794484 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.8306. Min Act: -0.0000

Data Index: 566186 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.7469. Min Act: -0.0000

Data Index: 278989 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6336. Min Act: -0.0000

Data Index: 415261 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1358985 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1924206 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6894. Min Act: -0.0000

Data Index: 644342 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6098. Min Act: -0.0000

Data Index: 756368 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6121. Min Act: -0.0000

Data Index: 691372 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1684912 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1292688 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.4851. Min Act: -0.0000

Data Index: 473086 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5822. Min Act: -0.0000

Data Index: 365802 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1134005 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5748. Min Act: -0.0000

Data Index: 586114 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1376959 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.4887. Min Act: -0.0000

Data Index: 205563 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5117. Min Act: -0.0000

Data Index: 968831 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5214. Min Act: -0.0000

Data Index: 939512 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.4963. Min Act: -0.0000

Data Index: 349506 (The Pile)

Max Activating Token Index: 545