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

Dataset: The Pile

Neuron 3545 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: 0.6267. Min Range: -0.6267

Max Act: 0.6267. Min Act: -0.0000

Data Index: 894458 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1960564 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5629. Min Act: -0.0000

Data Index: 140816 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1274324 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1137631 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1408032 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1926357 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4811. Min Act: -0.0000

Data Index: 936690 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1779960 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4913. Min Act: -0.0000

Data Index: 107262 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4827. Min Act: -0.0000

Data Index: 250085 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4960. Min Act: -0.0000

Data Index: 827012 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4898. Min Act: -0.0000

Data Index: 746691 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4654. Min Act: -0.0000

Data Index: 691095 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1592286 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4516. Min Act: -0.0000

Data Index: 946257 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4606. Min Act: -0.0000

Data Index: 423216 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4595. Min Act: -0.0000

Data Index: 710260 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4710. Min Act: -0.0000

Data Index: 66552 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4842. Min Act: -0.0000

Data Index: 595267 (The Pile)

Max Activating Token Index: 779