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

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

Neuron 3483 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5696. Min Act: -0.0002

Data Index: 1064033 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5501. Min Act: -0.0002

Data Index: 293125 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4999. Min Act: -0.0002

Data Index: 901152 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5073. Min Act: -0.0002

Data Index: 185491 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4628. Min Act: -0.0002

Data Index: 1219245 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5251. Min Act: -0.0002

Data Index: 191413 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4894. Min Act: -0.0002

Data Index: 586075 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4857. Min Act: -0.0002

Data Index: 402028 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5190. Min Act: -0.0002

Data Index: 460229 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4878. Min Act: -0.0002

Data Index: 229659 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5004. Min Act: -0.0002

Data Index: 950695 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4821. Min Act: -0.0002

Data Index: 1182210 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4945. Min Act: -0.0002

Data Index: 334079 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4882. Min Act: -0.0002

Data Index: 1217201 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5155. Min Act: -0.0002

Data Index: 917035 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4835. Min Act: -0.0002

Data Index: 1185648 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4859. Min Act: -0.0002

Data Index: 1297612 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4839. Min Act: -0.0002

Data Index: 1153705 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5144. Min Act: -0.0002

Data Index: 325528 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4475. Min Act: -0.0002

Data Index: 420405 (C4 (Web Text))

Max Activating Token Index: 247