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

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

Neuron 4825 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0000

Data Index: 778149 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1826. Min Act: -0.0000

Data Index: 541338 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1333215 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1745. Min Act: -0.0000

Data Index: 796255 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1865. Min Act: -0.0000

Data Index: 612112 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1064152 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1845. Min Act: -0.0000

Data Index: 181015 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1825. Min Act: -0.0000

Data Index: 147158 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1039956 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1161251 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1656. Min Act: -0.0000

Data Index: 197428 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1670. Min Act: -0.0000

Data Index: 828099 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1686. Min Act: -0.0000

Data Index: 970586 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1634. Min Act: -0.0000

Data Index: 553360 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1255806 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1569. Min Act: -0.0000

Data Index: 271015 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1618. Min Act: -0.0000

Data Index: 497584 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1633. Min Act: -0.0000

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1531. Min Act: -0.0000

Data Index: 678241 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1582. Min Act: -0.0000

Data Index: 830309 (C4 (Web Text))

Max Activating Token Index: 834