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

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

Neuron 2591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1869. Min Act: -0.0000

Data Index: 47942 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1775. Min Act: -0.0000

Data Index: 259029 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1245271 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1836. Min Act: -0.0000

Data Index: 85836 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1235715 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1740. Min Act: -0.0000

Data Index: 59439 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1719. Min Act: -0.0000

Data Index: 492617 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1807. Min Act: -0.0000

Data Index: 570701 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1756. Min Act: -0.0000

Data Index: 462442 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1520. Min Act: -0.0000

Data Index: 725466 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1568. Min Act: -0.0000

Data Index: 24721 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1537. Min Act: -0.0000

Data Index: 629622 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1527. Min Act: -0.0000

Data Index: 353946 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1624. Min Act: -0.0000

Data Index: 644866 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1562. Min Act: -0.0000

Data Index: 775237 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1308376 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1519. Min Act: -0.0000

Data Index: 912101 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1240347 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1420. Min Act: -0.0000

Data Index: 750952 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1418. Min Act: -0.0000

Data Index: 875416 (C4 (Web Text))

Max Activating Token Index: 549