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

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

Neuron 1807 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1579424 (Python Code)

Max Activating Token Index: 922

Text #1

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1515487 (Python Code)

Max Activating Token Index: 637

Text #2

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1468556 (Python Code)

Max Activating Token Index: 379

Text #3

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1436946 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1533611 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1539240 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1571568 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1523377 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1411571 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1449724 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1637519 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1642805 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1376193 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1433460 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1531806 (Python Code)

Max Activating Token Index: 494

Text #15

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1394637 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1390274 (Python Code)

Max Activating Token Index: 708

Text #17

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1374442 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1588280 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1439863 (Python Code)

Max Activating Token Index: 772