Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1120 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.2027. Min Act: -0.0005

Data Index: 1178744 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.2090. Min Act: -0.0006

Data Index: 14976 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1391. Min Act: -0.0006

Data Index: 1182129 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1770. Min Act: -0.0006

Data Index: 212475 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1700. Min Act: -0.0005

Data Index: 921979 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1694. Min Act: -0.0005

Data Index: 412986 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1744. Min Act: -0.0005

Data Index: 1271489 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1510. Min Act: -0.0006

Data Index: 869522 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1640. Min Act: -0.0005

Data Index: 89160 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1702. Min Act: -0.0006

Data Index: 1287521 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1690. Min Act: -0.0006

Data Index: 180678 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1623. Min Act: -0.0006

Data Index: 953732 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1741. Min Act: -0.0006

Data Index: 933339 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1445. Min Act: -0.0006

Data Index: 342234 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1604. Min Act: -0.0005

Data Index: 133710 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1610. Min Act: -0.0006

Data Index: 218350 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1595. Min Act: -0.0006

Data Index: 232526 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1654. Min Act: -0.0006

Data Index: 804598 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1484. Min Act: -0.0006

Data Index: 118689 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1648. Min Act: -0.0006

Data Index: 1158958 (C4 (Web Text))

Max Activating Token Index: 345