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

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

Neuron 1370 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1384. Min Range: -1.1384

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1583600 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1603143 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1241981 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5922. Min Act: -0.0000

Data Index: 727284 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5716. Min Act: -0.0000

Data Index: 355334 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1478637 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5759. Min Act: -0.0000

Data Index: 33927 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5776. Min Act: -0.0000

Data Index: 958038 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1553246 (Python Code)

Max Activating Token Index: 900

Text #9

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5417. Min Act: -0.0000

Data Index: 892806 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1649735 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1480124 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1640692 (Python Code)

Max Activating Token Index: 131

Text #13

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1031983 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.4754. Min Act: -0.0000

Data Index: 33710 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5012. Min Act: -0.0000

Data Index: 594715 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.4896. Min Act: -0.0000

Data Index: 611106 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1374889 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.5203. Min Act: -0.0000

Data Index: 111316 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1635210 (Python Code)

Max Activating Token Index: 656