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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1414 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1486977 (Python Code)

Max Activating Token Index: 496

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1632677 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1454893 (Python Code)

Max Activating Token Index: 879

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1570496 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1533599 (Python Code)

Max Activating Token Index: 559

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1391285 (Python Code)

Max Activating Token Index: 353

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1424226 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1486755 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1385086 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1518194 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1559039 (Python Code)

Max Activating Token Index: 613

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1451478 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1373903 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1611749 (Python Code)

Max Activating Token Index: 371

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1652724 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1378011 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1644681 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1374925 (Python Code)

Max Activating Token Index: 245

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1647076 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1640108 (Python Code)

Max Activating Token Index: 808