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

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

Neuron 3497 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2415. Min Act: -0.0003

Data Index: 1427077 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2109. Min Act: -0.0003

Data Index: 1645306 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2090. Min Act: -0.0003

Data Index: 1507040 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2093. Min Act: -0.0002

Data Index: 1446307 (Python Code)

Max Activating Token Index: 109

Text #4

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2011. Min Act: -0.0003

Data Index: 1646898 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2023. Min Act: -0.0002

Data Index: 1437533 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1993. Min Act: -0.0003

Data Index: 1442644 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1857. Min Act: -0.0003

Data Index: 1411849 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1955. Min Act: -0.0002

Data Index: 1413950 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2001. Min Act: -0.0003

Data Index: 1406741 (Python Code)

Max Activating Token Index: 534

Text #10

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1976. Min Act: -0.0003

Data Index: 1397031 (Python Code)

Max Activating Token Index: 595

Text #11

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1852. Min Act: -0.0003

Data Index: 1582811 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1909. Min Act: -0.0003

Data Index: 1370148 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1888. Min Act: -0.0002

Data Index: 1596800 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1946. Min Act: -0.0003

Data Index: 1541610 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1930. Min Act: -0.0003

Data Index: 1410565 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1925. Min Act: -0.0003

Data Index: 1361942 (Python Code)

Max Activating Token Index: 440

Text #17

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1844. Min Act: -0.0003

Data Index: 1461821 (Python Code)

Max Activating Token Index: 555

Text #18

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1834. Min Act: -0.0002

Data Index: 1477530 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1844. Min Act: -0.0003

Data Index: 1437151 (Python Code)

Max Activating Token Index: 226