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

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

Neuron 4708 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0002

Data Index: 424786 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1210. Min Act: -0.0002

Data Index: 800001 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1152. Min Act: -0.0002

Data Index: 613588 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1052. Min Act: -0.0002

Data Index: 670093 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1028. Min Act: -0.0002

Data Index: 373622 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0977. Min Act: -0.0002

Data Index: 271546 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1317379 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1513110 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1370614 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1390750 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1257309 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1476082 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1455483 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1479665 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1513286 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1536121 (Python Code)

Max Activating Token Index: 522

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1510985 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1430020 (Python Code)

Max Activating Token Index: 750

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1342141 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1547829 (Python Code)

Max Activating Token Index: 868