Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5445 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1103. Min Act: -0.0002

Data Index: 332190 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0002

Data Index: 192598 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1036. Min Act: -0.0002

Data Index: 457996 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1013. Min Act: -0.0002

Data Index: 746200 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0939. Min Act: -0.0002

Data Index: 237847 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0929. Min Act: -0.0002

Data Index: 767689 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0922. Min Act: -0.0002

Data Index: 798968 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0922. Min Act: -0.0002

Data Index: 216702 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1066624 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0896. Min Act: -0.0002

Data Index: 7732 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0857. Min Act: -0.0002

Data Index: 786435 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0889. Min Act: -0.0002

Data Index: 633280 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0855. Min Act: -0.0002

Data Index: 142698 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0878. Min Act: -0.0002

Data Index: 263677 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0873. Min Act: -0.0002

Data Index: 907246 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0909. Min Act: -0.0002

Data Index: 296033 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0848. Min Act: -0.0002

Data Index: 526204 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1238724 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1333028 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0845. Min Act: -0.0002

Data Index: 55567 (C4 (Web Text))

Max Activating Token Index: 97