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

Dataset: The Pile

Neuron 254 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: 0.4918. Min Range: -0.4918

Max Act: 0.4918. Min Act: -0.0000

Data Index: 137528 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4540. Min Act: -0.0000

Data Index: 244240 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3846. Min Act: -0.0000

Data Index: 357223 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4516. Min Act: -0.0000

Data Index: 336045 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1694442 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1654849 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1734719 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1998023 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3368. Min Act: -0.0000

Data Index: 768165 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1050657 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1401 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1562859 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1196767 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3685. Min Act: -0.0000

Data Index: 48044 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1662970 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3158. Min Act: -0.0000

Data Index: 153969 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3415. Min Act: -0.0000

Data Index: 156829 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3191. Min Act: -0.0000

Data Index: 921447 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1606865 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1154010 (The Pile)

Max Activating Token Index: 871