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

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

Neuron 1421 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: 0.2507. Min Range: -0.2507

Max Act: 0.2507. Min Act: -0.0002

Data Index: 1375656 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2404. Min Act: -0.0002

Data Index: 1529808 (Python Code)

Max Activating Token Index: 384

Text #2

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2165. Min Act: -0.0002

Data Index: 1398926 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2134. Min Act: -0.0002

Data Index: 1623795 (Python Code)

Max Activating Token Index: 932

Text #4

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2056. Min Act: -0.0002

Data Index: 1550736 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1733. Min Act: -0.0002

Data Index: 1473159 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2066. Min Act: -0.0002

Data Index: 1533937 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1882. Min Act: -0.0002

Data Index: 1519368 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1969. Min Act: -0.0002

Data Index: 1577378 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1856. Min Act: -0.0002

Data Index: 1376442 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1864. Min Act: -0.0002

Data Index: 1613247 (Python Code)

Max Activating Token Index: 404

Text #11

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1586340 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1818. Min Act: -0.0002

Data Index: 1509835 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1708. Min Act: -0.0002

Data Index: 1545219 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1934. Min Act: -0.0002

Data Index: 1499405 (Python Code)

Max Activating Token Index: 535

Text #15

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1756. Min Act: -0.0002

Data Index: 1377416 (Python Code)

Max Activating Token Index: 611

Text #16

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1820. Min Act: -0.0002

Data Index: 1576439 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1423346 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1765. Min Act: -0.0002

Data Index: 1656635 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1770. Min Act: -0.0002

Data Index: 1639210 (Python Code)

Max Activating Token Index: 919