Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3544 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4783. Min Act: -0.0002

Data Index: 99106 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4357. Min Act: -0.0003

Data Index: 1262752 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4013. Min Act: -0.0002

Data Index: 1032023 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4022. Min Act: -0.0002

Data Index: 476371 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3715. Min Act: -0.0002

Data Index: 960281 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3812. Min Act: -0.0002

Data Index: 116626 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3866. Min Act: -0.0002

Data Index: 216675 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3581. Min Act: -0.0002

Data Index: 1322536 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3770. Min Act: -0.0002

Data Index: 1735 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3669. Min Act: -0.0002

Data Index: 777075 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3685. Min Act: -0.0002

Data Index: 984456 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3434. Min Act: -0.0002

Data Index: 385034 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3472. Min Act: -0.0002

Data Index: 752199 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3572. Min Act: -0.0002

Data Index: 840556 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3654. Min Act: -0.0002

Data Index: 768096 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3622. Min Act: -0.0002

Data Index: 12477 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3284. Min Act: -0.0002

Data Index: 923365 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3394. Min Act: -0.0002

Data Index: 727980 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3177. Min Act: -0.0002

Data Index: 115216 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3427. Min Act: -0.0002

Data Index: 842080 (C4 (Web Text))

Max Activating Token Index: 567