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

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

Neuron 13 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.8467. Min Act: -0.0001

Data Index: 750786 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.8136. Min Act: -0.0001

Data Index: 1215015 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.7185. Min Act: -0.0001

Data Index: 181557 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6483. Min Act: -0.0001

Data Index: 986831 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6577. Min Act: -0.0001

Data Index: 801468 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5817. Min Act: -0.0001

Data Index: 620204 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5972. Min Act: -0.0001

Data Index: 978979 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5885. Min Act: -0.0001

Data Index: 281116 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6024. Min Act: -0.0001

Data Index: 602062 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6102. Min Act: -0.0001

Data Index: 443457 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5709. Min Act: -0.0001

Data Index: 1041674 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5917. Min Act: -0.0001

Data Index: 600276 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1061701 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5165. Min Act: -0.0001

Data Index: 105861 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5479. Min Act: -0.0001

Data Index: 297908 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5838. Min Act: -0.0001

Data Index: 211391 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5402. Min Act: -0.0001

Data Index: 21576 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.4926. Min Act: -0.0001

Data Index: 171732 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5102. Min Act: -0.0001

Data Index: 368591 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5387. Min Act: -0.0001

Data Index: 359562 (C4 (Web Text))

Max Activating Token Index: 17