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

Dataset: The Pile

Neuron 5100 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: 0.3321. Min Range: -0.3321

Max Act: 0.3321. Min Act: -0.0000

Data Index: 277319 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1971079 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1198183 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2584. Min Act: -0.0000

Data Index: 678743 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2350. Min Act: -0.0000

Data Index: 442278 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1424962 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2334. Min Act: -0.0000

Data Index: 471046 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2116. Min Act: -0.0000

Data Index: 811415 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1466433 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2173. Min Act: -0.0000

Data Index: 921768 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2300. Min Act: -0.0000

Data Index: 551219 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2116. Min Act: -0.0000

Data Index: 748013 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1615177 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1903007 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2034. Min Act: -0.0000

Data Index: 316856 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1621. Min Act: -0.0000

Data Index: 295444 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2065. Min Act: -0.0000

Data Index: 647979 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1436767 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1652324 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1811807 (The Pile)

Max Activating Token Index: 177