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

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

Neuron 2162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0000

Data Index: 28045 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0961. Min Act: -0.0000

Data Index: 107121 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1072. Min Act: -0.0000

Data Index: 445412 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1031289 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0961. Min Act: -0.0000

Data Index: 141830 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1194191 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1014. Min Act: -0.0000

Data Index: 744558 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0849. Min Act: -0.0000

Data Index: 952099 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0889. Min Act: -0.0000

Data Index: 148523 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1303994 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1154116 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1066410 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1210565 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0752. Min Act: -0.0000

Data Index: 655295 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0813. Min Act: -0.0000

Data Index: 444557 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0821. Min Act: -0.0000

Data Index: 350552 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0819. Min Act: -0.0000

Data Index: 460156 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0756. Min Act: -0.0000

Data Index: 808451 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0774. Min Act: -0.0000

Data Index: 229023 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0735. Min Act: -0.0000

Data Index: 188557 (C4 (Web Text))

Max Activating Token Index: 721