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

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

Neuron 727 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: 0.0876. Min Range: -0.0876

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1496975 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1362400 (Python Code)

Max Activating Token Index: 488

Text #2

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1478601 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1505231 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1605214 (Python Code)

Max Activating Token Index: 476

Text #5

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0852. Min Act: -0.0003

Data Index: 1449671 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1386055 (Python Code)

Max Activating Token Index: 985

Text #7

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1512816 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1573752 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1483939 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1428657 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1418061 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1502925 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1515501 (Python Code)

Max Activating Token Index: 35

Text #14

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1432057 (Python Code)

Max Activating Token Index: 994

Text #15

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1437243 (Python Code)

Max Activating Token Index: 870

Text #16

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1440716 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1434634 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1574927 (Python Code)

Max Activating Token Index: 389

Text #19

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1512215 (Python Code)

Max Activating Token Index: 271