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

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

Neuron 2603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4187. Min Range: -2.4187

Max Act: 2.4187. Min Act: -0.0000

Data Index: 1518168 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 2.4187. Min Range: -2.4187

Max Act: 2.2405. Min Act: -0.0000

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.9083. Min Act: -0.0000

Data Index: 919921 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 2.4187. Min Range: -2.4187

Max Act: 2.1865. Min Act: -0.0000

Data Index: 1496100 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.9998. Min Act: -0.0000

Data Index: 1433693 (Python Code)

Max Activating Token Index: 82

Text #5

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.9518. Min Act: -0.0000

Data Index: 735295 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.7812. Min Act: -0.0000

Data Index: 1638992 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.6664. Min Act: -0.0000

Data Index: 675188 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1382067 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.6461. Min Act: -0.0000

Data Index: 597906 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.6303. Min Act: -0.0000

Data Index: 1386185 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.5767. Min Act: -0.0000

Data Index: 1527001 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1616773 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1534758 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.6792. Min Act: -0.0000

Data Index: 1493849 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.5749. Min Act: -0.0000

Data Index: 1480043 (Python Code)

Max Activating Token Index: 407

Text #16

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.5685. Min Act: -0.0000

Data Index: 1650077 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.4842. Min Act: -0.0000

Data Index: 1638795 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.5108. Min Act: -0.0000

Data Index: 800269 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 2.4187. Min Range: -2.4187

Max Act: 1.4759. Min Act: -0.0000

Data Index: 133807 (C4 (Web Text))

Max Activating Token Index: 671