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

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

Neuron 1680 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0002

Data Index: 159759 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1238847 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0723. Min Act: -0.0002

Data Index: 911754 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0722. Min Act: -0.0002

Data Index: 204689 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0729. Min Act: -0.0002

Data Index: 630865 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1073848 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0756. Min Act: -0.0002

Data Index: 291319 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0700. Min Act: -0.0002

Data Index: 520223 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0691. Min Act: -0.0002

Data Index: 901823 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1146484 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1233817 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0693. Min Act: -0.0002

Data Index: 614444 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1224159 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0671. Min Act: -0.0002

Data Index: 410585 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0668. Min Act: -0.0002

Data Index: 834043 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0617. Min Act: -0.0002

Data Index: 837335 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0658. Min Act: -0.0002

Data Index: 240784 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0641. Min Act: -0.0002

Data Index: 127725 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1023218 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1174577 (C4 (Web Text))

Max Activating Token Index: 44