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

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

Neuron 3498 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1325437 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6162. Min Act: -0.0000

Data Index: 586478 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5751. Min Act: -0.0000

Data Index: 611670 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5859. Min Act: -0.0000

Data Index: 424892 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1264326 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1006136 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5118. Min Act: -0.0000

Data Index: 792592 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4696. Min Act: -0.0000

Data Index: 236429 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4926. Min Act: -0.0000

Data Index: 780165 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4903. Min Act: -0.0000

Data Index: 31915 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4823. Min Act: -0.0000

Data Index: 245878 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4525. Min Act: -0.0000

Data Index: 645338 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4363. Min Act: -0.0000

Data Index: 547188 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4424. Min Act: -0.0000

Data Index: 118062 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.3721. Min Act: -0.0000

Data Index: 39742 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4360. Min Act: -0.0000

Data Index: 334366 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4602. Min Act: -0.0000

Data Index: 344779 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4433. Min Act: -0.0000

Data Index: 199879 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4244. Min Act: -0.0000

Data Index: 345290 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1247934 (C4 (Web Text))

Max Activating Token Index: 920