Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1624 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2074. Min Act: -0.0002

Data Index: 1635398 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2061. Min Act: -0.0002

Data Index: 1080195 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1970. Min Act: -0.0002

Data Index: 1479184 (Python Code)

Max Activating Token Index: 601

Text #3

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2025. Min Act: -0.0002

Data Index: 1512062 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2005. Min Act: -0.0002

Data Index: 1491200 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1899. Min Act: -0.0002

Data Index: 1441116 (Python Code)

Max Activating Token Index: 353

Text #6

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1926. Min Act: -0.0002

Data Index: 1406427 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1829. Min Act: -0.0002

Data Index: 1605148 (Python Code)

Max Activating Token Index: 950

Text #8

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1838. Min Act: -0.0002

Data Index: 1521463 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1829. Min Act: -0.0002

Data Index: 1447204 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1706. Min Act: -0.0002

Data Index: 1581098 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1752. Min Act: -0.0002

Data Index: 1545294 (Python Code)

Max Activating Token Index: 779

Text #12

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1810. Min Act: -0.0001

Data Index: 1586181 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1815. Min Act: -0.0002

Data Index: 1553442 (Python Code)

Max Activating Token Index: 208

Text #14

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1745. Min Act: -0.0002

Data Index: 1288430 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1724. Min Act: -0.0002

Data Index: 1436610 (Python Code)

Max Activating Token Index: 322

Text #16

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1855. Min Act: -0.0002

Data Index: 1435508 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1772. Min Act: -0.0002

Data Index: 1588415 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1720. Min Act: -0.0002

Data Index: 1602951 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1782. Min Act: -0.0002

Data Index: 1437995 (Python Code)

Max Activating Token Index: 219