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

Dataset: The Pile

Neuron 1549 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1847621 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1995291 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.1972. Min Act: -0.0000

Data Index: 904059 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1701634 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1455047 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1463836 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0810. Min Act: -0.0000

Data Index: 606284 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0788. Min Act: -0.0000

Data Index: 905913 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0684. Min Act: -0.0000

Data Index: 613218 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0643. Min Act: -0.0000

Data Index: 619134 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1427346 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1414868 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1802327 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1807756 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0602. Min Act: -0.0000

Data Index: 823508 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0578. Min Act: -0.0000

Data Index: 766584 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1150831 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1776709 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0544. Min Act: -0.0000

Data Index: 680491 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1442074 (The Pile)

Max Activating Token Index: 1023