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

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

Neuron 3654 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1460984 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1640564 (Python Code)

Max Activating Token Index: 379

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1149779 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1193415 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0765. Min Act: -0.0000

Data Index: 748007 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1579723 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1492983 (Python Code)

Max Activating Token Index: 607

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1493008 (Python Code)

Max Activating Token Index: 588

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1632637 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1599343 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1374193 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1520232 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1460660 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1419440 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1618996 (Python Code)

Max Activating Token Index: 432

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1457213 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1500633 (Python Code)

Max Activating Token Index: 671

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0576. Min Act: -0.0000

Data Index: 972288 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1432165 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1515106 (Python Code)

Max Activating Token Index: 777