Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 67 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0684. Min Act: -0.0003

Data Index: 609279 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0556. Min Act: -0.0003

Data Index: 652776 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0697. Min Act: -0.0003

Data Index: 538577 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1187736 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0003

Data Index: 823896 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0660. Min Act: -0.0003

Data Index: 377851 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0648. Min Act: -0.0003

Data Index: 306701 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0676. Min Act: -0.0003

Data Index: 565004 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0685. Min Act: -0.0003

Data Index: 709500 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1323094 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1456726 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0600. Min Act: -0.0003

Data Index: 32537 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1320700 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0556. Min Act: -0.0003

Data Index: 643679 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0617. Min Act: -0.0003

Data Index: 867304 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1194547 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0604. Min Act: -0.0003

Data Index: 375227 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0557. Min Act: -0.0003

Data Index: 463860 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0557. Min Act: -0.0003

Data Index: 248974 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1339859 (C4 (Web Text))

Max Activating Token Index: 85