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

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

Neuron 4344 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: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1342886 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0721. Min Act: -0.0002

Data Index: 880067 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0660. Min Act: -0.0002

Data Index: 67295 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0606. Min Act: -0.0002

Data Index: 120871 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0644. Min Act: -0.0002

Data Index: 78345 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0607. Min Act: -0.0002

Data Index: 995516 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0654. Min Act: -0.0002

Data Index: 208308 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0606. Min Act: -0.0002

Data Index: 176666 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0637. Min Act: -0.0002

Data Index: 273815 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0682. Min Act: -0.0002

Data Index: 519031 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0594. Min Act: -0.0002

Data Index: 312914 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1287000 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0605. Min Act: -0.0002

Data Index: 931636 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0611. Min Act: -0.0002

Data Index: 67363 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1016136 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0606. Min Act: -0.0002

Data Index: 470510 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0626. Min Act: -0.0002

Data Index: 336299 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0629. Min Act: -0.0002

Data Index: 782224 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0589. Min Act: -0.0002

Data Index: 709905 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0538. Min Act: -0.0002

Data Index: 867404 (C4 (Web Text))

Max Activating Token Index: 967