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

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

Neuron 2572 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: 0.7013. Min Range: -0.7013

Max Act: 0.6750. Min Act: -0.0001

Data Index: 549009 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.7013. Min Act: -0.0000

Data Index: 377465 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6182. Min Act: -0.0001

Data Index: 658037 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6263. Min Act: -0.0001

Data Index: 484877 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5702. Min Act: -0.0000

Data Index: 564874 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6065. Min Act: -0.0000

Data Index: 732674 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5875. Min Act: -0.0000

Data Index: 603482 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6377. Min Act: -0.0001

Data Index: 280468 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5923. Min Act: -0.0000

Data Index: 989829 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5923. Min Act: -0.0001

Data Index: 1283780 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5923. Min Act: -0.0001

Data Index: 682791 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5923. Min Act: -0.0001

Data Index: 274513 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6032. Min Act: -0.0001

Data Index: 242162 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6219. Min Act: -0.0001

Data Index: 2476 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5404. Min Act: -0.0001

Data Index: 498691 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1036526 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1035545 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5823. Min Act: -0.0001

Data Index: 896385 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5803. Min Act: -0.0000

Data Index: 874148 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6196. Min Act: -0.0001

Data Index: 552023 (C4 (Web Text))

Max Activating Token Index: 582