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

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

Neuron 5391 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.6758. Min Act: -0.0000

Data Index: 914889 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.2308. Min Act: -0.0000

Data Index: 1052977 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.2032. Min Act: -0.0000

Data Index: 1093839 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.1271. Min Act: -0.0000

Data Index: 1131152 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.1107. Min Act: -0.0000

Data Index: 536609 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.2023. Min Act: -0.0000

Data Index: 1208348 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.0691. Min Act: -0.0000

Data Index: 422830 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1022246 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.0139. Min Act: -0.0000

Data Index: 1346535 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.9072. Min Act: -0.0000

Data Index: 886033 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.8100. Min Act: -0.0000

Data Index: 1276655 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.9021. Min Act: -0.0000

Data Index: 1158457 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.9047. Min Act: -0.0000

Data Index: 1220925 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 2.6758. Min Range: -2.6758

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1176701 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.8602. Min Act: -0.0000

Data Index: 1103472 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1240613 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.6839. Min Act: -0.0000

Data Index: 624165 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.7777. Min Act: -0.0000

Data Index: 129190 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.6755. Min Act: -0.0000

Data Index: 812812 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.6758. Min Range: -2.6758

Max Act: 1.7766. Min Act: -0.0000

Data Index: 1028893 (C4 (Web Text))

Max Activating Token Index: 968