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

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

Neuron 3418 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.2050. Min Act: -0.0001

Data Index: 1236410 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.2152. Min Act: -0.0002

Data Index: 605887 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.2021. Min Act: -0.0002

Data Index: 1045725 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1907. Min Act: -0.0002

Data Index: 779437 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.2100. Min Act: -0.0001

Data Index: 546622 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.2169. Min Act: -0.0001

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1860. Min Act: -0.0002

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1977. Min Act: -0.0001

Data Index: 67254 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1926. Min Act: -0.0001

Data Index: 353993 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1938. Min Act: -0.0001

Data Index: 122985 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1702. Min Act: -0.0002

Data Index: 1082464 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1829. Min Act: -0.0002

Data Index: 239763 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1813. Min Act: -0.0002

Data Index: 176717 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1674. Min Act: -0.0002

Data Index: 774960 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1868. Min Act: -0.0002

Data Index: 1148607 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1054302 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1618. Min Act: -0.0001

Data Index: 37674 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1597. Min Act: -0.0002

Data Index: 125702 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1762. Min Act: -0.0001

Data Index: 74297 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.2169. Min Range: -0.2169

Max Act: 0.1633. Min Act: -0.0002

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 463