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

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

Neuron 222 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0000

Data Index: 753428 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1320933 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1328733 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0721. Min Act: -0.0000

Data Index: 914727 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0761. Min Act: -0.0000

Data Index: 146221 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0698. Min Act: -0.0000

Data Index: 752659 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1043749 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1015483 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1225084 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0672. Min Act: -0.0000

Data Index: 409458 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0601. Min Act: -0.0000

Data Index: 653457 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0622. Min Act: -0.0000

Data Index: 373959 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1029343 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0618. Min Act: -0.0000

Data Index: 476824 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0611. Min Act: 0.0000

Data Index: 310016 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0564. Min Act: -0.0000

Data Index: 810651 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1193416 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0592. Min Act: 0.0000

Data Index: 1122942 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0566. Min Act: -0.0000

Data Index: 634716 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1131483 (C4 (Web Text))

Max Activating Token Index: 492