Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1681 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1442186 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1458379 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1500137 (Python Code)

Max Activating Token Index: 491

Text #3

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1459046 (Python Code)

Max Activating Token Index: 850

Text #4

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1634478 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1428784 (Python Code)

Max Activating Token Index: 519

Text #6

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1436654 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1550831 (Python Code)

Max Activating Token Index: 553

Text #8

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1585047 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0805. Min Act: -0.0000

Data Index: 658034 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1561501 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1409552 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1601524 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1452754 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1530068 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0730. Min Act: -0.0000

Data Index: 19074 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1564060 (Python Code)

Max Activating Token Index: 878

Text #17

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1523861 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1518120 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1574299 (Python Code)

Max Activating Token Index: 202