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

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

Neuron 3196 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: 0.0851. Min Range: -0.0851

Max Act: 0.0824. Min Act: -0.0002

Data Index: 80163 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1169318 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1041114 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0782. Min Act: -0.0002

Data Index: 478869 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0782. Min Act: -0.0002

Data Index: 724746 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1010016 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0748. Min Act: -0.0002

Data Index: 732937 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0756. Min Act: -0.0002

Data Index: 245155 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0713. Min Act: -0.0002

Data Index: 640572 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0710. Min Act: -0.0002

Data Index: 509797 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0698. Min Act: -0.0002

Data Index: 978379 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1140786 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0676. Min Act: -0.0002

Data Index: 930495 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0675. Min Act: -0.0002

Data Index: 228483 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1328947 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0665. Min Act: -0.0002

Data Index: 285354 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0657. Min Act: -0.0002

Data Index: 357339 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0647. Min Act: -0.0002

Data Index: 290601 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1281796 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0642. Min Act: -0.0002

Data Index: 419828 (C4 (Web Text))

Max Activating Token Index: 339