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

Dataset: The Pile

Neuron 2930 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.4878. Min Act: -0.0000

Data Index: 950855 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1215795 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.4604. Min Act: -0.0000

Data Index: 208902 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.2880. Min Act: -0.0000

Data Index: 597132 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1946328 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1094120 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1004742 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1440. Min Act: -0.0000

Data Index: 996510 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1790306 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1274594 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0281. Min Act: -0.0000

Data Index: 680261 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1283. Min Act: -0.0000

Data Index: 364579 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0302. Min Act: -0.0000

Data Index: 883546 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 1.4878. Min Range: -1.4878

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1441142 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1483381 (The Pile)

Max Activating Token Index: 620

Text #15

Max Range: 1.4878. Min Range: -1.4878

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1524779 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1681554 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 1.4878. Min Range: -1.4878

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1831346 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0590. Min Act: -0.0000

Data Index: 906100 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1244661 (The Pile)

Max Activating Token Index: 824