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

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

Neuron 399 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0003

Data Index: 53675 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1078. Min Act: -0.0003

Data Index: 270102 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1012. Min Act: -0.0002

Data Index: 444432 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1014. Min Act: -0.0003

Data Index: 761198 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0989. Min Act: -0.0003

Data Index: 182598 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1001. Min Act: -0.0003

Data Index: 134452 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0935. Min Act: -0.0003

Data Index: 50268 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0882. Min Act: -0.0003

Data Index: 1193929 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0925. Min Act: -0.0003

Data Index: 335138 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0840. Min Act: -0.0003

Data Index: 930011 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0863. Min Act: -0.0003

Data Index: 229828 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1189217 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0846. Min Act: -0.0003

Data Index: 51728 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0824. Min Act: -0.0003

Data Index: 364410 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0801. Min Act: -0.0002

Data Index: 927985 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0783. Min Act: -0.0003

Data Index: 154000 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0780. Min Act: -0.0003

Data Index: 384106 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0794. Min Act: -0.0003

Data Index: 896828 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0752. Min Act: -0.0003

Data Index: 861215 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1222994 (C4 (Web Text))

Max Activating Token Index: 461