Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0000

Data Index: 493558 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0697. Min Act: -0.0001

Data Index: 315825 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0730. Min Act: -0.0000

Data Index: 251154 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1071341 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0696. Min Act: -0.0000

Data Index: 561591 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0670. Min Act: -0.0000

Data Index: 199894 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0636. Min Act: -0.0000

Data Index: 589631 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0656. Min Act: -0.0001

Data Index: 847048 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0627. Min Act: -0.0000

Data Index: 216682 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0643. Min Act: -0.0000

Data Index: 304911 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1056109 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1157280 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0610. Min Act: -0.0000

Data Index: 426664 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0580. Min Act: -0.0000

Data Index: 47629 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0567. Min Act: -0.0001

Data Index: 562919 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0597. Min Act: -0.0000

Data Index: 347416 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1171411 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0590. Min Act: -0.0001

Data Index: 496991 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0590. Min Act: -0.0000

Data Index: 742523 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1146513 (C4 (Web Text))

Max Activating Token Index: 560