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

Dataset: The Pile

Neuron 1698 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1639825 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5857. Min Act: -0.0000

Data Index: 225531 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1158703 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1804165 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1572765 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1775196 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1320759 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1859456 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1267418 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1410924 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5094. Min Act: -0.0000

Data Index: 656408 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1103318 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4491. Min Act: -0.0000

Data Index: 98333 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4905. Min Act: -0.0000

Data Index: 578019 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1880764 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1403990 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4009. Min Act: -0.0000

Data Index: 108050 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4354. Min Act: -0.0000

Data Index: 894483 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1388222 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5155. Min Act: -0.0000

Data Index: 909234 (The Pile)

Max Activating Token Index: 111