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

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

Neuron 2177 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0000

Data Index: 388348 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1023. Min Act: -0.0000

Data Index: 914845 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0895. Min Act: -0.0000

Data Index: 467236 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0918. Min Act: -0.0000

Data Index: 422031 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1149713 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0844. Min Act: -0.0000

Data Index: 191664 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1167891 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0824. Min Act: -0.0000

Data Index: 93446 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0845. Min Act: -0.0000

Data Index: 51571 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1211668 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0843. Min Act: -0.0000

Data Index: 211290 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1543596 (Python Code)

Max Activating Token Index: 213

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1175017 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0703. Min Act: -0.0000

Data Index: 583859 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1260416 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1146971 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1355016 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0708. Min Act: -0.0000

Data Index: 51375 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0699. Min Act: -0.0000

Data Index: 635099 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0697. Min Act: -0.0000

Data Index: 855580 (C4 (Web Text))

Max Activating Token Index: 257