Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.2109. Min Act: -0.0000

Data Index: 943522 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1987. Min Act: -0.0001

Data Index: 692243 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1034703 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1963. Min Act: -0.0001

Data Index: 182121 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1348144 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1836. Min Act: -0.0000

Data Index: 840852 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1773. Min Act: -0.0000

Data Index: 184487 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1807. Min Act: -0.0000

Data Index: 100818 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1801. Min Act: -0.0001

Data Index: 989334 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1991. Min Act: -0.0000

Data Index: 670442 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1218484 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1217249 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1111122 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1800. Min Act: -0.0000

Data Index: 167980 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1556. Min Act: -0.0000

Data Index: 607364 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1295808 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1238951 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1699. Min Act: -0.0000

Data Index: 756542 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1096466 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1668. Min Act: -0.0001

Data Index: 392289 (C4 (Web Text))

Max Activating Token Index: 89