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

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

Neuron 2700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1610. Min Act: -0.0002

Data Index: 105524 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1654. Min Act: -0.0002

Data Index: 904139 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1825. Min Act: -0.0002

Data Index: 139833 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1581. Min Act: -0.0002

Data Index: 1122424 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1664. Min Act: -0.0002

Data Index: 1096536 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1593. Min Act: -0.0002

Data Index: 750162 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1685. Min Act: -0.0002

Data Index: 1153254 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1708. Min Act: -0.0002

Data Index: 1219019 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1732. Min Act: -0.0002

Data Index: 1241515 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1774. Min Act: -0.0002

Data Index: 1315153 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1745. Min Act: -0.0002

Data Index: 1256613 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1829. Min Act: -0.0002

Data Index: 364143 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0002

Data Index: 1233089 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1598. Min Act: -0.0002

Data Index: 608231 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1807. Min Act: -0.0002

Data Index: 1065133 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1820. Min Act: -0.0002

Data Index: 1242300 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1614. Min Act: -0.0002

Data Index: 928836 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1770. Min Act: -0.0002

Data Index: 683120 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1812. Min Act: -0.0002

Data Index: 570928 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1523. Min Act: -0.0002

Data Index: 923885 (C4 (Web Text))

Max Activating Token Index: 809