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

Dataset: The Pile

Neuron 3032 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: 6.9237. Min Range: -6.9237

Max Act: 6.9237. Min Act: -0.0000

Data Index: 98044 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 6.9237. Min Range: -6.9237

Max Act: 6.3183. Min Act: -0.0000

Data Index: 1468341 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 6.9237. Min Range: -6.9237

Max Act: 6.3149. Min Act: -0.0000

Data Index: 762591 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.9117. Min Act: -0.0000

Data Index: 1209131 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 6.9237. Min Range: -6.9237

Max Act: 6.0043. Min Act: -0.0000

Data Index: 1385836 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.8038. Min Act: -0.0000

Data Index: 1121472 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.3187. Min Act: -0.0000

Data Index: 1086963 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.6260. Min Act: -0.0000

Data Index: 1581335 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.5234. Min Act: -0.0000

Data Index: 940533 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.4779. Min Act: -0.0000

Data Index: 1889656 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.5029. Min Act: -0.0000

Data Index: 1253743 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.4586. Min Act: -0.0000

Data Index: 1631552 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.6206. Min Act: -0.0000

Data Index: 1047311 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.3957. Min Act: -0.0000

Data Index: 603926 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.1009. Min Act: -0.0000

Data Index: 1723015 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.4635. Min Act: -0.0000

Data Index: 1025837 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.2279. Min Act: -0.0000

Data Index: 1257703 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.4593. Min Act: -0.0000

Data Index: 1398045 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.4168. Min Act: -0.0000

Data Index: 1087629 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 6.9237. Min Range: -6.9237

Max Act: 5.3731. Min Act: -0.0000

Data Index: 62499 (The Pile)

Max Activating Token Index: 49