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

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

Neuron 4255 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0886. Min Act: -0.0000

Data Index: 950374 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1206263 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1432203 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0000

Data Index: 872978 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1433125 (Python Code)

Max Activating Token Index: 374

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0868. Min Act: -0.0000

Data Index: 207839 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1196912 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0876. Min Act: -0.0000

Data Index: 906850 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1214459 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0775. Min Act: -0.0000

Data Index: 442718 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0669. Min Act: -0.0000

Data Index: 253737 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0753. Min Act: -0.0000

Data Index: 340395 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0718. Min Act: -0.0000

Data Index: 410024 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0705. Min Act: -0.0000

Data Index: 802128 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0729. Min Act: -0.0000

Data Index: 547039 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1095876 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1473150 (Python Code)

Max Activating Token Index: 162

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1502530 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1556910 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1312447 (C4 (Web Text))

Max Activating Token Index: 993