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

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

Neuron 4813 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: 0.1116. Min Range: -0.1116

Max Act: 0.1116. Min Act: -0.0003

Data Index: 1227588 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0966. Min Act: -0.0003

Data Index: 1247284 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0967. Min Act: -0.0003

Data Index: 1109389 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0966. Min Act: -0.0003

Data Index: 385810 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0946. Min Act: -0.0003

Data Index: 977725 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0941. Min Act: -0.0003

Data Index: 67643 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0915. Min Act: -0.0003

Data Index: 787071 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0914. Min Act: -0.0003

Data Index: 337906 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0894. Min Act: -0.0003

Data Index: 822895 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0890. Min Act: -0.0003

Data Index: 611371 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0873. Min Act: -0.0003

Data Index: 365230 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0911. Min Act: -0.0003

Data Index: 671098 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0834. Min Act: -0.0002

Data Index: 205892 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0846. Min Act: -0.0003

Data Index: 365832 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0853. Min Act: -0.0003

Data Index: 12113 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0850. Min Act: -0.0003

Data Index: 1192203 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0849. Min Act: -0.0003

Data Index: 881233 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0839. Min Act: -0.0003

Data Index: 658003 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0831. Min Act: -0.0003

Data Index: 451465 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0845. Min Act: -0.0003

Data Index: 66668 (C4 (Web Text))

Max Activating Token Index: 761