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

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

Neuron 635 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: 0.0915. Min Range: -0.0915

Max Act: 0.0854. Min Act: -0.0003

Data Index: 746133 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0915. Min Act: -0.0003

Data Index: 996163 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0808. Min Act: -0.0003

Data Index: 406990 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0797. Min Act: -0.0003

Data Index: 197242 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1197833 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0673. Min Act: -0.0003

Data Index: 210563 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0772. Min Act: -0.0003

Data Index: 284580 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0793. Min Act: -0.0003

Data Index: 168270 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0594. Min Act: -0.0003

Data Index: 238472 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0625. Min Act: -0.0003

Data Index: 569186 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0664. Min Act: -0.0003

Data Index: 702170 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0749. Min Act: -0.0003

Data Index: 1079313 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1240992 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1056780 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1123391 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1032206 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0653. Min Act: -0.0003

Data Index: 917185 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1088114 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0603. Min Act: -0.0003

Data Index: 24763 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0651. Min Act: -0.0003

Data Index: 170549 (C4 (Web Text))

Max Activating Token Index: 284