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

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

Neuron 3834 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1107727 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6227. Min Act: -0.0000

Data Index: 1047902 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6922. Min Act: -0.0000

Data Index: 589081 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.4133. Min Act: -0.0000

Data Index: 806722 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.3752. Min Act: -0.0000

Data Index: 747986 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.3160. Min Act: -0.0000

Data Index: 74168 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.2890. Min Act: -0.0000

Data Index: 349917 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.3647. Min Act: -0.0000

Data Index: 566674 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.3902. Min Act: -0.0000

Data Index: 862286 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.3651. Min Act: -0.0000

Data Index: 913313 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.2610. Min Act: -0.0000

Data Index: 372159 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1006815 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1160600 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.2106. Min Act: -0.0000

Data Index: 916111 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1341205 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.1480. Min Act: -0.0000

Data Index: 944742 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1306835 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.1513. Min Act: -0.0000

Data Index: 806374 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1128157 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1054991 (C4 (Web Text))

Max Activating Token Index: 821