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

Dataset: The Pile

Neuron 60 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: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1174174 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0736. Min Act: 0.0000

Data Index: 1713345 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0734. Min Act: 0.0000

Data Index: 953607 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0705. Min Act: 0.0000

Data Index: 1846455 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0695. Min Act: 0.0000

Data Index: 25834 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0696. Min Act: 0.0000

Data Index: 1641658 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0691. Min Act: 0.0000

Data Index: 1669427 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0686. Min Act: 0.0000

Data Index: 1084144 (The Pile)

Max Activating Token Index: 12

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0677. Min Act: 0.0000

Data Index: 1915167 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0676. Min Act: 0.0000

Data Index: 706475 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0668. Min Act: 0.0000

Data Index: 704982 (The Pile)

Max Activating Token Index: 4

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1716187 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0664. Min Act: 0.0000

Data Index: 253266 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0659. Min Act: -0.0000

Data Index: 899188 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1794646 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0656. Min Act: 0.0000

Data Index: 731098 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0644. Min Act: 0.0000

Data Index: 900047 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0642. Min Act: 0.0000

Data Index: 963691 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0643. Min Act: -0.0000

Data Index: 548032 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0638. Min Act: 0.0000

Data Index: 675769 (The Pile)

Max Activating Token Index: 3