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

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

Neuron 1396 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0770. Min Act: -0.0000

Data Index: 419332 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0000

Data Index: 722684 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0795. Min Act: -0.0000

Data Index: 249227 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0731. Min Act: -0.0000

Data Index: 634838 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0755. Min Act: -0.0000

Data Index: 712783 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0711. Min Act: -0.0000

Data Index: 371799 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0675. Min Act: -0.0000

Data Index: 378614 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0706. Min Act: -0.0000

Data Index: 886229 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1099963 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1241578 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0664. Min Act: -0.0000

Data Index: 860884 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0670. Min Act: -0.0000

Data Index: 275060 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0684. Min Act: -0.0000

Data Index: 276370 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0608. Min Act: -0.0000

Data Index: 562246 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1356482 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0614. Min Act: -0.0000

Data Index: 399228 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0636. Min Act: -0.0000

Data Index: 108672 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0640. Min Act: -0.0000

Data Index: 112260 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0650. Min Act: -0.0000

Data Index: 557189 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0618. Min Act: -0.0000

Data Index: 115140 (C4 (Web Text))

Max Activating Token Index: 365