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

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

Neuron 893 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0001

Data Index: 92993 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1240. Min Act: -0.0001

Data Index: 846192 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1155007 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1054. Min Act: -0.0001

Data Index: 963141 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1116. Min Act: -0.0001

Data Index: 337273 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0992. Min Act: -0.0001

Data Index: 803854 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0980. Min Act: -0.0001

Data Index: 369127 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0972. Min Act: -0.0001

Data Index: 402765 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1127929 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0936. Min Act: -0.0001

Data Index: 431121 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1128643 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0955. Min Act: -0.0001

Data Index: 342901 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0943. Min Act: -0.0001

Data Index: 58263 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1076317 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0984. Min Act: -0.0001

Data Index: 782559 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1226165 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0908. Min Act: -0.0001

Data Index: 134913 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1256631 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0922. Min Act: -0.0001

Data Index: 647555 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0900. Min Act: -0.0001

Data Index: 489010 (C4 (Web Text))

Max Activating Token Index: 137