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

Dataset: The Pile

Neuron 1433 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1125429 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1621737 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6456. Min Act: -0.0000

Data Index: 151127 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1919088 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6676. Min Act: -0.0000

Data Index: 849272 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6986. Min Act: -0.0000

Data Index: 942414 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1855686 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6471. Min Act: -0.0000

Data Index: 204499 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1740467 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6537. Min Act: -0.0000

Data Index: 198649 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5012. Min Act: -0.0000

Data Index: 757635 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1985555 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6281. Min Act: -0.0000

Data Index: 699697 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1902528 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1924829 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1048176 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5863. Min Act: -0.0000

Data Index: 649933 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1212433 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6478. Min Act: -0.0000

Data Index: 671932 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1551629 (The Pile)

Max Activating Token Index: 644