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

Dataset: The Pile

Neuron 4272 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: 5.1101. Min Range: -5.1101

Max Act: 4.4502. Min Act: -0.0000

Data Index: 1227047 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 5.1101. Min Range: -5.1101

Max Act: 5.1101. Min Act: -0.0000

Data Index: 826842 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 5.1101. Min Range: -5.1101

Max Act: 4.3754. Min Act: -0.0000

Data Index: 201715 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 5.1101. Min Range: -5.1101

Max Act: 4.4678. Min Act: -0.0000

Data Index: 1385221 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 5.1101. Min Range: -5.1101

Max Act: 4.1123. Min Act: -0.0000

Data Index: 1501551 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 5.1101. Min Range: -5.1101

Max Act: 4.1664. Min Act: -0.0000

Data Index: 1974229 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.9037. Min Act: -0.0000

Data Index: 23585 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 5.1101. Min Range: -5.1101

Max Act: 4.3794. Min Act: -0.0000

Data Index: 1340480 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 5.1101. Min Range: -5.1101

Max Act: 4.2350. Min Act: -0.0000

Data Index: 802284 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.6568. Min Act: -0.0000

Data Index: 965818 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.8546. Min Act: -0.0000

Data Index: 706363 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.8393. Min Act: -0.0000

Data Index: 1567271 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.9824. Min Act: -0.0000

Data Index: 560093 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.8246. Min Act: -0.0000

Data Index: 1725482 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 5.1101. Min Range: -5.1101

Max Act: 4.4542. Min Act: -0.0000

Data Index: 1509047 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.7248. Min Act: -0.0000

Data Index: 901796 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.5176. Min Act: -0.0000

Data Index: 1312357 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.8483. Min Act: -0.0000

Data Index: 449625 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.5104. Min Act: -0.0000

Data Index: 85574 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 5.1101. Min Range: -5.1101

Max Act: 3.5146. Min Act: -0.0000

Data Index: 1007981 (The Pile)

Max Activating Token Index: 647