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

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

Neuron 512 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: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0003

Data Index: 797711 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0878. Min Act: -0.0003

Data Index: 614588 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1039424 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0786. Min Act: -0.0003

Data Index: 301670 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0799. Min Act: -0.0003

Data Index: 1206202 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0820. Min Act: -0.0003

Data Index: 192644 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0767. Min Act: -0.0003

Data Index: 927268 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0758. Min Act: -0.0002

Data Index: 232295 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0772. Min Act: -0.0003

Data Index: 984108 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0766. Min Act: -0.0003

Data Index: 702534 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0724. Min Act: -0.0003

Data Index: 153676 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0726. Min Act: -0.0003

Data Index: 1257776 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1238474 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0745. Min Act: -0.0003

Data Index: 40812 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0772. Min Act: -0.0003

Data Index: 1228881 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1290758 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0757. Min Act: -0.0002

Data Index: 544126 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0740. Min Act: -0.0003

Data Index: 415222 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0721. Min Act: -0.0002

Data Index: 234366 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1185106 (C4 (Web Text))

Max Activating Token Index: 579