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

Dataset: The Pile

Neuron 74 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.9200. Min Act: -0.0000

Data Index: 1219302 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1350913 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.9603. Min Act: -0.0000

Data Index: 417774 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.8594. Min Act: -0.0000

Data Index: 429816 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.9586. Min Act: -0.0000

Data Index: 1014356 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6895. Min Act: -0.0000

Data Index: 135514 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7965. Min Act: -0.0000

Data Index: 1952950 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7644. Min Act: -0.0000

Data Index: 404194 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1048571 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7635. Min Act: -0.0000

Data Index: 884185 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7508. Min Act: -0.0000

Data Index: 954486 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7248. Min Act: -0.0000

Data Index: 1947789 (The Pile)

Max Activating Token Index: 744

Text #12

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7263. Min Act: -0.0000

Data Index: 1085326 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7270. Min Act: -0.0000

Data Index: 913495 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7119. Min Act: -0.0000

Data Index: 706865 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7102. Min Act: -0.0000

Data Index: 312409 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7203. Min Act: -0.0000

Data Index: 1233365 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6098. Min Act: -0.0000

Data Index: 429429 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7019. Min Act: -0.0000

Data Index: 689927 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6834. Min Act: -0.0000

Data Index: 1751966 (The Pile)

Max Activating Token Index: 941