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

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

Neuron 1087 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: 0.2744. Min Range: -0.2744

Max Act: 0.2744. Min Act: -0.0002

Data Index: 1639647 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2229. Min Act: -0.0002

Data Index: 1567822 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2170. Min Act: -0.0002

Data Index: 1518947 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2073. Min Act: -0.0002

Data Index: 1380584 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1994. Min Act: -0.0002

Data Index: 1412933 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1949. Min Act: -0.0002

Data Index: 1553764 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1917. Min Act: -0.0002

Data Index: 1630251 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1837. Min Act: -0.0002

Data Index: 1575995 (Python Code)

Max Activating Token Index: 993

Text #8

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1771. Min Act: -0.0002

Data Index: 1616775 (Python Code)

Max Activating Token Index: 697

Text #9

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1866. Min Act: -0.0002

Data Index: 1446851 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1798. Min Act: -0.0002

Data Index: 1396994 (Python Code)

Max Activating Token Index: 744

Text #11

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1915. Min Act: -0.0002

Data Index: 1483981 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1726. Min Act: -0.0002

Data Index: 1396581 (Python Code)

Max Activating Token Index: 260

Text #13

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1772. Min Act: -0.0002

Data Index: 1466397 (Python Code)

Max Activating Token Index: 339

Text #14

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1787. Min Act: -0.0002

Data Index: 1472563 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1728. Min Act: -0.0002

Data Index: 1486600 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1785. Min Act: -0.0002

Data Index: 1403489 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1702. Min Act: -0.0002

Data Index: 1480454 (Python Code)

Max Activating Token Index: 390

Text #18

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1710. Min Act: -0.0002

Data Index: 1525671 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1743. Min Act: -0.0002

Data Index: 1535618 (Python Code)

Max Activating Token Index: 165