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

Dataset: The Pile

Neuron 3493 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: 0.8107. Min Range: -0.8107

Max Act: 0.8107. Min Act: -0.0000

Data Index: 769042 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1893201 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1344991 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1466488 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5549. Min Act: -0.0000

Data Index: 812934 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4780. Min Act: -0.0000

Data Index: 49630 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5092. Min Act: -0.0000

Data Index: 515005 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1757895 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1781732 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1966062 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4262. Min Act: -0.0000

Data Index: 954368 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4092. Min Act: -0.0000

Data Index: 197836 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1126273 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1634926 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.3864. Min Act: -0.0000

Data Index: 724040 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1523405 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4043. Min Act: -0.0000

Data Index: 710870 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.3644. Min Act: -0.0000

Data Index: 721214 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1164419 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.4010. Min Act: -0.0000

Data Index: 419453 (The Pile)

Max Activating Token Index: 423