Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 367 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0003

Data Index: 70380 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0835. Min Act: -0.0004

Data Index: 395664 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1333785 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0793. Min Act: -0.0003

Data Index: 313564 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0757. Min Act: -0.0003

Data Index: 559375 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0762. Min Act: -0.0003

Data Index: 988930 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0715. Min Act: -0.0003

Data Index: 105891 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0726. Min Act: -0.0003

Data Index: 638844 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0780. Min Act: -0.0003

Data Index: 940203 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1124097 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1129705 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0718. Min Act: -0.0003

Data Index: 564036 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1092884 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0700. Min Act: -0.0003

Data Index: 86768 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0698. Min Act: -0.0003

Data Index: 292110 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0687. Min Act: -0.0003

Data Index: 951728 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1037540 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0681. Min Act: -0.0003

Data Index: 548226 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1010441 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0691. Min Act: -0.0003

Data Index: 63901 (C4 (Web Text))

Max Activating Token Index: 56