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

Dataset: The Pile

Neuron 4062 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1302155 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1975178 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1181615 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.9021. Min Act: 0.0000

Data Index: 10554 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1812910 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1578956 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1642122 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1128617 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1853646 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8200. Min Act: 0.0000

Data Index: 806913 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7852. Min Act: -0.0000

Data Index: 128138 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1417914 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7942. Min Act: 0.0000

Data Index: 1278735 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1975635 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1889050 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1033708 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7562. Min Act: 0.0000

Data Index: 549277 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1235130 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7482. Min Act: -0.0000

Data Index: 336709 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.9992. Min Range: -0.9992

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1884471 (The Pile)

Max Activating Token Index: 939