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

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

Neuron 92 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: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1233877 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1283908 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0667. Min Act: -0.0003

Data Index: 516403 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0644. Min Act: -0.0003

Data Index: 551378 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0640. Min Act: -0.0003

Data Index: 943636 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1200362 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1010178 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0625. Min Act: -0.0003

Data Index: 723080 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0610. Min Act: -0.0003

Data Index: 600341 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0626. Min Act: -0.0004

Data Index: 1270103 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1006932 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0617. Min Act: -0.0002

Data Index: 40833 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0636. Min Act: -0.0003

Data Index: 809479 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0627. Min Act: -0.0002

Data Index: 435403 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0599. Min Act: -0.0004

Data Index: 270860 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0618. Min Act: -0.0003

Data Index: 776494 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0607. Min Act: -0.0003

Data Index: 240954 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0601. Min Act: -0.0002

Data Index: 322175 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0591. Min Act: -0.0003

Data Index: 523757 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0567. Min Act: -0.0003

Data Index: 699129 (C4 (Web Text))

Max Activating Token Index: 980