Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1397291 (Python Code)

Max Activating Token Index: 66

Text #1

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1392614 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1411259 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1626706 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1462796 (Python Code)

Max Activating Token Index: 430

Text #5

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1391333 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1649962 (Python Code)

Max Activating Token Index: 885

Text #7

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1547284 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1420357 (Python Code)

Max Activating Token Index: 323

Text #9

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1590397 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1812. Min Act: -0.0001

Data Index: 1496186 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1611799 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1488866 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1101738 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1453909 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1586233 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1553486 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1837. Min Act: -0.0001

Data Index: 1485908 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1595209 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1533126 (Python Code)

Max Activating Token Index: 23