Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3756 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1018754 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1060791 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6907. Min Act: -0.0000

Data Index: 524966 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7037. Min Act: -0.0000

Data Index: 443110 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1414080 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1515374 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6159. Min Act: -0.0000

Data Index: 452899 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6122. Min Act: -0.0000

Data Index: 813102 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1018642 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6368. Min Act: -0.0000

Data Index: 73357 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1311609 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1891896 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5871. Min Act: -0.0000

Data Index: 388878 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1146140 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1556519 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1919374 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1439007 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6075. Min Act: -0.0000

Data Index: 202440 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1975443 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5676. Min Act: -0.0000

Data Index: 323854 (The Pile)

Max Activating Token Index: 39