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

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

Neuron 3630 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: 0.0755. Min Range: -0.0755

Max Act: 0.0755. Min Act: -0.0003

Data Index: 323097 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0718. Min Act: -0.0003

Data Index: 419209 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1035076 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0683. Min Act: -0.0002

Data Index: 266392 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0627. Min Act: -0.0003

Data Index: 9158 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0642. Min Act: -0.0003

Data Index: 593366 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1058182 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0596. Min Act: -0.0003

Data Index: 871187 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0583. Min Act: -0.0003

Data Index: 530241 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0571. Min Act: -0.0002

Data Index: 411356 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0578. Min Act: -0.0003

Data Index: 953299 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1153101 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1002759 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1251460 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1226799 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1170046 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0556. Min Act: -0.0003

Data Index: 136915 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0534. Min Act: -0.0003

Data Index: 546217 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1264626 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0512. Min Act: -0.0002

Data Index: 81508 (C4 (Web Text))

Max Activating Token Index: 260