Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0962. Min Act: -0.0003

Data Index: 370001 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0856. Min Act: -0.0003

Data Index: 462630 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0897. Min Act: -0.0003

Data Index: 355917 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0854. Min Act: -0.0003

Data Index: 626658 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0881. Min Act: -0.0003

Data Index: 704803 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0846. Min Act: -0.0003

Data Index: 658919 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0826. Min Act: -0.0003

Data Index: 1348453 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1256664 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0756. Min Act: -0.0003

Data Index: 122544 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1167526 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0830. Min Act: -0.0003

Data Index: 477547 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0798. Min Act: -0.0003

Data Index: 283658 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0799. Min Act: -0.0003

Data Index: 539814 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0823. Min Act: -0.0003

Data Index: 651416 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0812. Min Act: -0.0003

Data Index: 208293 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0771. Min Act: -0.0003

Data Index: 476896 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1332364 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0823. Min Act: -0.0003

Data Index: 995008 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0785. Min Act: -0.0003

Data Index: 922194 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0811. Min Act: -0.0003

Data Index: 624029 (C4 (Web Text))

Max Activating Token Index: 771