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

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

Neuron 4771 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.9704. Min Act: -0.0001

Data Index: 347099 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.6515. Min Act: -0.0001

Data Index: 1604750 (Python Code)

Max Activating Token Index: 260

Text #2

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.5012. Min Act: -0.0000

Data Index: 639354 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.5652. Min Act: -0.0001

Data Index: 478615 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.4033. Min Act: -0.0001

Data Index: 1594536 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1308378 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.3599. Min Act: -0.0001

Data Index: 1497201 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.3240. Min Act: -0.0001

Data Index: 1294209 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.2816. Min Act: -0.0001

Data Index: 1445935 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.3370. Min Act: -0.0000

Data Index: 151526 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.2687. Min Act: -0.0000

Data Index: 951678 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.3630. Min Act: -0.0001

Data Index: 295606 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.4925. Min Act: -0.0001

Data Index: 833600 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.4511. Min Act: -0.0001

Data Index: 985011 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.3294. Min Act: -0.0001

Data Index: 780443 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1606146 (Python Code)

Max Activating Token Index: 184

Text #16

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.2958. Min Act: -0.0000

Data Index: 1539760 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.2888. Min Act: -0.0001

Data Index: 1503356 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.3204. Min Act: -0.0000

Data Index: 334312 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.9704. Min Range: -1.9704

Max Act: 1.2656. Min Act: -0.0000

Data Index: 476663 (C4 (Web Text))

Max Activating Token Index: 744