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

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

Neuron 1920 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0811. Min Act: -0.0001

Data Index: 532862 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0834. Min Act: -0.0000

Data Index: 686280 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1144741 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0778. Min Act: -0.0001

Data Index: 872703 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0700. Min Act: -0.0001

Data Index: 213115 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1111758 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0702. Min Act: -0.0001

Data Index: 285289 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0675. Min Act: -0.0000

Data Index: 862312 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0745. Min Act: -0.0000

Data Index: 209186 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0742. Min Act: -0.0000

Data Index: 515419 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0780. Min Act: -0.0000

Data Index: 132727 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0705. Min Act: -0.0000

Data Index: 591481 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1329476 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0694. Min Act: -0.0000

Data Index: 398569 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0683. Min Act: -0.0001

Data Index: 675063 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0701. Min Act: -0.0001

Data Index: 215012 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0655. Min Act: -0.0000

Data Index: 778940 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1272713 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0678. Min Act: -0.0000

Data Index: 980452 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0694. Min Act: -0.0000

Data Index: 609749 (C4 (Web Text))

Max Activating Token Index: 38