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

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

Neuron 4856 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: 2.5047. Min Range: -2.5047

Max Act: 2.5047. Min Act: -0.0000

Data Index: 426569 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 2.5047. Min Range: -2.5047

Max Act: 2.2392. Min Act: -0.0000

Data Index: 164290 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 2.5047. Min Range: -2.5047

Max Act: 2.2092. Min Act: -0.0000

Data Index: 726440 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 2.5047. Min Range: -2.5047

Max Act: 2.0705. Min Act: -0.0000

Data Index: 249734 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 2.5047. Min Range: -2.5047

Max Act: 2.2171. Min Act: -0.0000

Data Index: 1037133 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 2.5047. Min Range: -2.5047

Max Act: 2.1666. Min Act: -0.0000

Data Index: 783050 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 2.5047. Min Range: -2.5047

Max Act: 2.2335. Min Act: -0.0000

Data Index: 1172668 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.9722. Min Act: -0.0000

Data Index: 148391 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.9205. Min Act: -0.0000

Data Index: 730817 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.9130. Min Act: -0.0000

Data Index: 921302 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.8040. Min Act: -0.0000

Data Index: 419965 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.8936. Min Act: -0.0000

Data Index: 460071 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.8933. Min Act: -0.0000

Data Index: 994050 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.9870. Min Act: -0.0000

Data Index: 12480 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.8570. Min Act: -0.0000

Data Index: 685624 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.8527. Min Act: -0.0000

Data Index: 553030 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.7265. Min Act: -0.0000

Data Index: 88773 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.8040. Min Act: -0.0000

Data Index: 1062606 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.7905. Min Act: -0.0000

Data Index: 695514 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.6588. Min Act: -0.0000

Data Index: 1356576 (C4 (Web Text))

Max Activating Token Index: 86