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

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

Neuron 1683 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1144. Min Range: -8.1144

Max Act: 8.0219. Min Act: -0.0000

Data Index: 969332 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 8.1144. Min Range: -8.1144

Max Act: 8.1144. Min Act: -0.0000

Data Index: 502531 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 8.1144. Min Range: -8.1144

Max Act: 7.9519. Min Act: -0.0000

Data Index: 1320223 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 8.1144. Min Range: -8.1144

Max Act: 6.6939. Min Act: -0.0000

Data Index: 954894 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 8.1144. Min Range: -8.1144

Max Act: 6.0917. Min Act: -0.0000

Data Index: 903593 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.8893. Min Act: -0.0000

Data Index: 1011708 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 8.1144. Min Range: -8.1144

Max Act: 6.0083. Min Act: -0.0000

Data Index: 940302 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.4447. Min Act: -0.0000

Data Index: 1006171 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.7084. Min Act: -0.0000

Data Index: 1122273 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.2923. Min Act: -0.0000

Data Index: 156502 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.2821. Min Act: -0.0000

Data Index: 1091949 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.7859. Min Act: -0.0000

Data Index: 1142923 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.1800. Min Act: -0.0000

Data Index: 229183 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.4685. Min Act: -0.0000

Data Index: 1094589 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 8.1144. Min Range: -8.1144

Max Act: 5.1204. Min Act: -0.0000

Data Index: 889566 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 8.1144. Min Range: -8.1144

Max Act: 4.8546. Min Act: -0.0000

Data Index: 1107967 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 8.1144. Min Range: -8.1144

Max Act: 4.8494. Min Act: -0.0000

Data Index: 949746 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 8.1144. Min Range: -8.1144

Max Act: 4.8654. Min Act: -0.0000

Data Index: 9380 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 8.1144. Min Range: -8.1144

Max Act: 4.6664. Min Act: -0.0000

Data Index: 816545 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 8.1144. Min Range: -8.1144

Max Act: 4.6375. Min Act: -0.0000

Data Index: 1229774 (C4 (Web Text))

Max Activating Token Index: 977