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

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

Neuron 1898 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1138223 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6808. Min Act: -0.0000

Data Index: 652837 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6914. Min Act: -0.0000

Data Index: 186187 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6377. Min Act: -0.0000

Data Index: 864554 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6201. Min Act: -0.0000

Data Index: 995956 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1324535 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5769. Min Act: -0.0000

Data Index: 38640 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6274. Min Act: -0.0000

Data Index: 954051 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5534. Min Act: -0.0000

Data Index: 957742 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1101519 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5582. Min Act: -0.0000

Data Index: 757202 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6029. Min Act: -0.0000

Data Index: 125318 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5438. Min Act: -0.0000

Data Index: 929977 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1083951 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1124407 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1234778 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4842. Min Act: 0.0000

Data Index: 224196 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1298703 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5258. Min Act: -0.0000

Data Index: 651712 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4985. Min Act: -0.0000

Data Index: 218804 (C4 (Web Text))

Max Activating Token Index: 959