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

Dataset: The Pile

Neuron 3838 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: 1.0667. Min Range: -1.0667

Max Act: 0.9611. Min Act: -0.0000

Data Index: 80773 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1015448 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 1.0667. Min Range: -1.0667

Max Act: 1.0667. Min Act: -0.0000

Data Index: 665645 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1445218 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1133962 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1645916 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1772155 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1090833 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1859089 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9304. Min Act: -0.0000

Data Index: 226097 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1340661 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7890. Min Act: -0.0000

Data Index: 733254 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1936144 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7906. Min Act: -0.0000

Data Index: 197851 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1265016 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7787. Min Act: -0.0000

Data Index: 417306 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6959. Min Act: -0.0000

Data Index: 164733 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7286. Min Act: -0.0000

Data Index: 171065 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1865577 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1809194 (The Pile)

Max Activating Token Index: 411