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

Dataset: The Pile

Neuron 3680 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: 0.8447. Min Range: -0.8447

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1345247 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1830211 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.7772. Min Act: 0.0000

Data Index: 1100895 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1992373 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.7006. Min Act: -0.0000

Data Index: 203041 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1357787 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6515. Min Act: -0.0000

Data Index: 270532 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6531. Min Act: -0.0000

Data Index: 662813 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6311. Min Act: -0.0000

Data Index: 183870 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6722. Min Act: -0.0000

Data Index: 202729 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6524. Min Act: -0.0000

Data Index: 59114 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1207800 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1893789 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6323. Min Act: -0.0000

Data Index: 429149 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1625569 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1295619 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1268204 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6127. Min Act: -0.0000

Data Index: 232191 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.5905. Min Act: -0.0000

Data Index: 400575 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.5974. Min Act: -0.0000

Data Index: 983003 (The Pile)

Max Activating Token Index: 768