Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 510 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1047. Min Act: -0.0003

Data Index: 409200 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1006. Min Act: -0.0004

Data Index: 949775 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0004

Data Index: 1088593 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1021. Min Act: -0.0003

Data Index: 129217 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1010. Min Act: -0.0003

Data Index: 995099 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0975. Min Act: -0.0003

Data Index: 193171 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1042. Min Act: -0.0003

Data Index: 39203 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1022. Min Act: -0.0003

Data Index: 133013 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0993. Min Act: -0.0003

Data Index: 12140 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1048. Min Act: -0.0003

Data Index: 1382701 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1042. Min Act: -0.0003

Data Index: 738901 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0986. Min Act: -0.0003

Data Index: 878891 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1014. Min Act: -0.0003

Data Index: 912659 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0976. Min Act: -0.0003

Data Index: 241929 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1016. Min Act: -0.0003

Data Index: 909534 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1034. Min Act: -0.0003

Data Index: 128302 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0993. Min Act: -0.0003

Data Index: 992023 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1007. Min Act: -0.0003

Data Index: 272140 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0987. Min Act: -0.0003

Data Index: 47299 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0987. Min Act: -0.0003

Data Index: 219181 (C4 (Web Text))

Max Activating Token Index: 402