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

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

Neuron 3526 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8217. Min Range: -2.8217

Max Act: 2.6097. Min Act: 0.0000

Data Index: 848461 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 2.8217. Min Range: -2.8217

Max Act: 2.8217. Min Act: 0.0000

Data Index: 304000 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 2.8217. Min Range: -2.8217

Max Act: 2.1954. Min Act: -0.0000

Data Index: 59175 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 2.8217. Min Range: -2.8217

Max Act: 2.1635. Min Act: -0.0000

Data Index: 72854 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.9735. Min Act: 0.0000

Data Index: 990880 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.9375. Min Act: -0.0000

Data Index: 617089 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.9167. Min Act: 0.0001

Data Index: 641168 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.8193. Min Act: -0.0000

Data Index: 636187 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.8328. Min Act: -0.0000

Data Index: 653423 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.7370. Min Act: -0.0000

Data Index: 679773 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.7363. Min Act: 0.0000

Data Index: 280697 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.7234. Min Act: -0.0000

Data Index: 1092827 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.8199. Min Act: 0.0000

Data Index: 636435 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.5792. Min Act: 0.0000

Data Index: 481960 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.6529. Min Act: 0.0001

Data Index: 162306 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.5606. Min Act: -0.0000

Data Index: 97556 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.7271. Min Act: -0.0000

Data Index: 610548 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.6074. Min Act: -0.0000

Data Index: 310073 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.6992. Min Act: -0.0000

Data Index: 743815 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 2.8217. Min Range: -2.8217

Max Act: 1.6914. Min Act: -0.0000

Data Index: 949417 (C4 (Web Text))

Max Activating Token Index: 549