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

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

Neuron 719 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1390655 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1632604 (Python Code)

Max Activating Token Index: 291

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1368113 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1641242 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1398520 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1477648 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1420776 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1521644 (Python Code)

Max Activating Token Index: 519

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1475853 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1626186 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1474383 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1424107 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1586552 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1365543 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1484811 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1406931 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1435446 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1461918 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1459346 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1564369 (Python Code)

Max Activating Token Index: 86