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

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

Neuron 5083 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2627. Min Range: -4.2627

Max Act: 4.0825. Min Act: -0.0000

Data Index: 1427884 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 4.2627. Min Range: -4.2627

Max Act: 4.2627. Min Act: -0.0000

Data Index: 890353 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.7222. Min Act: -0.0000

Data Index: 1646164 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.4638. Min Act: -0.0000

Data Index: 1469737 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.6828. Min Act: -0.0000

Data Index: 1587060 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.2414. Min Act: -0.0000

Data Index: 1399093 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.4705. Min Act: -0.0000

Data Index: 1640531 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.2740. Min Act: -0.0000

Data Index: 941379 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 4.2627. Min Range: -4.2627

Max Act: 2.8558. Min Act: -0.0000

Data Index: 1448023 (Python Code)

Max Activating Token Index: 769

Text #9

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.1121. Min Act: -0.0000

Data Index: 880418 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.0890. Min Act: -0.0000

Data Index: 1419313 (Python Code)

Max Activating Token Index: 519

Text #11

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.2196. Min Act: -0.0000

Data Index: 1366594 (Python Code)

Max Activating Token Index: 959

Text #12

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.2964. Min Act: -0.0000

Data Index: 1540407 (Python Code)

Max Activating Token Index: 1010

Text #13

Max Range: 4.2627. Min Range: -4.2627

Max Act: 3.0796. Min Act: -0.0000

Data Index: 1429122 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 4.2627. Min Range: -4.2627

Max Act: 2.7578. Min Act: -0.0000

Data Index: 1409169 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 4.2627. Min Range: -4.2627

Max Act: 2.5841. Min Act: -0.0000

Data Index: 1017054 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 4.2627. Min Range: -4.2627

Max Act: 2.5363. Min Act: -0.0000

Data Index: 1453830 (Python Code)

Max Activating Token Index: 890

Text #17

Max Range: 4.2627. Min Range: -4.2627

Max Act: 2.9451. Min Act: -0.0000

Data Index: 1404872 (Python Code)

Max Activating Token Index: 225

Text #18

Max Range: 4.2627. Min Range: -4.2627

Max Act: 2.8924. Min Act: -0.0000

Data Index: 937407 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 4.2627. Min Range: -4.2627

Max Act: 2.6078. Min Act: -0.0000

Data Index: 1437831 (Python Code)

Max Activating Token Index: 241