Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5910 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2638. Min Act: -0.0000

Data Index: 155395 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1176769 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2037. Min Act: -0.0000

Data Index: 848949 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1887. Min Act: -0.0000

Data Index: 605913 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2078. Min Act: -0.0000

Data Index: 37951 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2034. Min Act: -0.0000

Data Index: 514583 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1044054 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1877. Min Act: -0.0000

Data Index: 484964 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1918. Min Act: -0.0000

Data Index: 117834 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1912. Min Act: -0.0000

Data Index: 936339 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1887. Min Act: -0.0000

Data Index: 796762 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1878. Min Act: -0.0000

Data Index: 942571 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1877. Min Act: -0.0000

Data Index: 702454 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1839. Min Act: -0.0000

Data Index: 159998 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1893. Min Act: -0.0000

Data Index: 673396 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1322694 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1798. Min Act: -0.0000

Data Index: 27389 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1923. Min Act: -0.0000

Data Index: 397234 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1864. Min Act: -0.0000

Data Index: 229375 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1296608 (C4 (Web Text))

Max Activating Token Index: 121