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

Dataset: The Pile

Neuron 1114 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: 0.6251. Min Range: -0.6251

Max Act: 0.6251. Min Act: -0.0000

Data Index: 138114 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4796. Min Act: -0.0000

Data Index: 48580 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1372500 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4954. Min Act: -0.0000

Data Index: 85949 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1046349 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1264861 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1729102 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1469080 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4700. Min Act: -0.0000

Data Index: 66242 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1818582 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4573. Min Act: -0.0000

Data Index: 285128 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4259. Min Act: -0.0000

Data Index: 63338 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4413. Min Act: -0.0000

Data Index: 578324 (The Pile)

Max Activating Token Index: 490

Text #13

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4407. Min Act: -0.0000

Data Index: 233615 (The Pile)

Max Activating Token Index: 497

Text #14

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1486727 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1674448 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1392511 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1824188 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1946502 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1273707 (The Pile)

Max Activating Token Index: 774