Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2916 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1982. Min Act: -0.0000

Data Index: 619683 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2294. Min Act: -0.0000

Data Index: 973030 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1997. Min Act: -0.0000

Data Index: 512433 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1265592 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1932. Min Act: -0.0000

Data Index: 268393 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1839. Min Act: -0.0000

Data Index: 578779 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1140599 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1215452 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1859. Min Act: -0.0000

Data Index: 558027 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1854. Min Act: -0.0000

Data Index: 278118 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1015652 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1827. Min Act: -0.0000

Data Index: 827784 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1799. Min Act: -0.0000

Data Index: 221735 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1714. Min Act: -0.0000

Data Index: 421037 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1219615 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1092054 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1694. Min Act: -0.0000

Data Index: 427541 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1695. Min Act: -0.0000

Data Index: 792264 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1628. Min Act: -0.0000

Data Index: 219507 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1684. Min Act: -0.0000

Data Index: 120972 (C4 (Web Text))

Max Activating Token Index: 309