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

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

Neuron 611 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: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0002

Data Index: 796387 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2322. Min Act: -0.0002

Data Index: 71172 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2357. Min Act: -0.0002

Data Index: 1412566 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2244. Min Act: -0.0002

Data Index: 605859 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2195. Min Act: -0.0002

Data Index: 1436876 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1607532 (Python Code)

Max Activating Token Index: 627

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2077. Min Act: -0.0002

Data Index: 778658 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2152. Min Act: -0.0001

Data Index: 1562426 (Python Code)

Max Activating Token Index: 740

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2121. Min Act: -0.0002

Data Index: 207641 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2088. Min Act: -0.0002

Data Index: 1521551 (Python Code)

Max Activating Token Index: 422

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2143. Min Act: -0.0002

Data Index: 1529742 (Python Code)

Max Activating Token Index: 458

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2062. Min Act: -0.0002

Data Index: 1363571 (Python Code)

Max Activating Token Index: 419

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2024. Min Act: -0.0002

Data Index: 1192063 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1957. Min Act: -0.0002

Data Index: 1564502 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1481285 (Python Code)

Max Activating Token Index: 940

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1859. Min Act: -0.0002

Data Index: 148014 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1831. Min Act: -0.0002

Data Index: 1376975 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2001. Min Act: -0.0002

Data Index: 83154 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1791. Min Act: -0.0002

Data Index: 1600004 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1132637 (C4 (Web Text))

Max Activating Token Index: 150