Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1404. Min Range: -3.1404

Max Act: 3.1404. Min Act: -0.0000

Data Index: 1586896 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.7860. Min Act: -0.0000

Data Index: 1545017 (Python Code)

Max Activating Token Index: 169

Text #2

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.8230. Min Act: -0.0000

Data Index: 1623966 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.4265. Min Act: -0.0000

Data Index: 1404572 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.4272. Min Act: -0.0000

Data Index: 1648884 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.3848. Min Act: -0.0000

Data Index: 1539346 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1597909 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.3138. Min Act: -0.0000

Data Index: 1609432 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.3188. Min Act: -0.0000

Data Index: 1585752 (Python Code)

Max Activating Token Index: 413

Text #9

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.3652. Min Act: -0.0000

Data Index: 1471369 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.3987. Min Act: -0.0000

Data Index: 1505512 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.2718. Min Act: -0.0000

Data Index: 1649854 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.3996. Min Act: -0.0000

Data Index: 1418044 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1440. Min Act: -0.0000

Data Index: 1571968 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.2095. Min Act: -0.0000

Data Index: 1473993 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1919. Min Act: -0.0000

Data Index: 1368648 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 3.1404. Min Range: -3.1404

Max Act: 1.9632. Min Act: -0.0000

Data Index: 1627338 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1633. Min Act: -0.0000

Data Index: 1542610 (Python Code)

Max Activating Token Index: 575

Text #18

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.4077. Min Act: -0.0000

Data Index: 1524000 (Python Code)

Max Activating Token Index: 519

Text #19

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.0407. Min Act: -0.0000

Data Index: 1452287 (Python Code)

Max Activating Token Index: 164