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

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

Neuron 3404 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1588047 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1453315 (Python Code)

Max Activating Token Index: 199

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1476032 (Python Code)

Max Activating Token Index: 533

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1511922 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1635642 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1594132 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1561387 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1462010 (Python Code)

Max Activating Token Index: 375

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1500536 (Python Code)

Max Activating Token Index: 752

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1370152 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1530355 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1364987 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1485973 (Python Code)

Max Activating Token Index: 983

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1563443 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1602970 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1397481 (Python Code)

Max Activating Token Index: 871

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1391941 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1491234 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1379951 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1552960 (Python Code)

Max Activating Token Index: 10