Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1307. Min Act: -0.0002

Data Index: 888102 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0834. Min Act: -0.0002

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0863. Min Act: -0.0002

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1564060 (Python Code)

Max Activating Token Index: 814

Text #4

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1641725 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0853. Min Act: -0.0002

Data Index: 782536 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1404330 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0780. Min Act: -0.0002

Data Index: 672789 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1037468 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0857. Min Act: -0.0002

Data Index: 949337 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1595659 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0712. Min Act: -0.0002

Data Index: 360661 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1035505 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1513491 (Python Code)

Max Activating Token Index: 704

Text #14

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0688. Min Act: -0.0002

Data Index: 534100 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1385715 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1459046 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0560. Min Act: -0.0002

Data Index: 296147 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1368412 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0683. Min Act: -0.0003

Data Index: 1504280 (Python Code)

Max Activating Token Index: 103