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

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

Neuron 290 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9905. Min Act: -0.0000

Data Index: 64675 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8087. Min Act: -0.0000

Data Index: 827562 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6860. Min Act: -0.0000

Data Index: 87509 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7158. Min Act: -0.0000

Data Index: 833250 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1433739 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5886. Min Act: -0.0000

Data Index: 610484 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1637878 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1190837 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1580182 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5200. Min Act: -0.0000

Data Index: 843474 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.4927. Min Act: -0.0000

Data Index: 974045 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5007. Min Act: -0.0000

Data Index: 658409 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5396. Min Act: -0.0000

Data Index: 541761 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1070979 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5190. Min Act: -0.0000

Data Index: 732686 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.4907. Min Act: -0.0000

Data Index: 389121 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.4651. Min Act: -0.0000

Data Index: 665721 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5029. Min Act: -0.0000

Data Index: 371060 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.4554. Min Act: -0.0000

Data Index: 873748 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.4707. Min Act: -0.0000

Data Index: 393912 (C4 (Web Text))

Max Activating Token Index: 332