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

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

Neuron 2384 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2281. Min Act: -0.0000

Data Index: 2666 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2049. Min Act: -0.0000

Data Index: 395963 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1148008 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2032. Min Act: -0.0000

Data Index: 20419 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1402878 (Python Code)

Max Activating Token Index: 969

Text #5

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1868. Min Act: -0.0000

Data Index: 700859 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1639406 (Python Code)

Max Activating Token Index: 938

Text #7

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1792. Min Act: -0.0000

Data Index: 661676 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1059295 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1266849 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1589. Min Act: -0.0000

Data Index: 469412 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1164366 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1291500 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1708. Min Act: -0.0000

Data Index: 825761 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1641. Min Act: -0.0000

Data Index: 223230 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1603. Min Act: -0.0000

Data Index: 953944 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1885. Min Act: -0.0000

Data Index: 343887 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1627. Min Act: -0.0000

Data Index: 335163 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1561. Min Act: -0.0000

Data Index: 24586 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1379876 (Python Code)

Max Activating Token Index: 498