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

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

Neuron 191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1966. Min Act: -0.0001

Data Index: 936067 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1976. Min Act: -0.0001

Data Index: 557453 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1875. Min Act: -0.0001

Data Index: 948552 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1793. Min Act: -0.0001

Data Index: 456836 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1686. Min Act: -0.0001

Data Index: 277032 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1019419 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1747. Min Act: -0.0001

Data Index: 917041 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1779. Min Act: -0.0001

Data Index: 651018 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1713. Min Act: -0.0001

Data Index: 139904 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1205801 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1282370 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1701. Min Act: -0.0001

Data Index: 338073 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1649. Min Act: -0.0001

Data Index: 871334 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1243178 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1591. Min Act: -0.0001

Data Index: 684737 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1630. Min Act: -0.0001

Data Index: 115828 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1500. Min Act: -0.0001

Data Index: 1606987 (Python Code)

Max Activating Token Index: 405

Text #17

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1636. Min Act: -0.0001

Data Index: 745375 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1467. Min Act: -0.0001

Data Index: 244330 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1718. Min Act: -0.0001

Data Index: 194550 (C4 (Web Text))

Max Activating Token Index: 742