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

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

Neuron 2783 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2867. Min Act: -0.0000

Data Index: 550951 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2838. Min Act: -0.0000

Data Index: 332952 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2537. Min Act: -0.0000

Data Index: 84005 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1979. Min Act: -0.0000

Data Index: 837773 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1166502 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1949. Min Act: -0.0000

Data Index: 207018 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1991. Min Act: -0.0000

Data Index: 57346 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1891. Min Act: -0.0000

Data Index: 468423 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1867. Min Act: -0.0000

Data Index: 57664 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1866. Min Act: -0.0000

Data Index: 977106 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1864. Min Act: -0.0000

Data Index: 691356 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1697. Min Act: -0.0000

Data Index: 9271 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1235844 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1756. Min Act: -0.0000

Data Index: 959827 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1723. Min Act: -0.0000

Data Index: 631121 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1340267 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1778. Min Act: -0.0000

Data Index: 839101 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1720. Min Act: -0.0000

Data Index: 616803 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1315469 (C4 (Web Text))

Max Activating Token Index: 138