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

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

Neuron 32 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: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0002

Data Index: 742146 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0837. Min Act: -0.0002

Data Index: 975019 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1646300 (Python Code)

Max Activating Token Index: 927

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0757. Min Act: -0.0002

Data Index: 590532 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1408896 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0755. Min Act: -0.0002

Data Index: 19032 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0745. Min Act: -0.0002

Data Index: 832595 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0776. Min Act: -0.0002

Data Index: 530511 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1194782 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0675. Min Act: -0.0002

Data Index: 975970 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1450400 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1264873 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0710. Min Act: -0.0002

Data Index: 89702 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0665. Min Act: -0.0002

Data Index: 122926 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1614176 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1418477 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0619. Min Act: -0.0002

Data Index: 729045 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1619777 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0627. Min Act: -0.0002

Data Index: 350909 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0652. Min Act: -0.0002

Data Index: 308324 (C4 (Web Text))

Max Activating Token Index: 938