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

Dataset: The Pile

Neuron 4687 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.7113. Min Act: -0.0000

Data Index: 273192 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6689. Min Act: -0.0000

Data Index: 323362 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1418994 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6014. Min Act: -0.0000

Data Index: 73418 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5833. Min Act: -0.0000

Data Index: 434171 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1698391 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1564840 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5643. Min Act: -0.0000

Data Index: 695539 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1147808 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1617884 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1308073 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1629757 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1780722 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1597087 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5110. Min Act: -0.0000

Data Index: 158473 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4833. Min Act: -0.0000

Data Index: 857463 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1191823 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4723. Min Act: -0.0000

Data Index: 231556 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4862. Min Act: -0.0000

Data Index: 454272 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1395059 (The Pile)

Max Activating Token Index: 610