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

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

Neuron 3938 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: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0002

Data Index: 705143 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0976. Min Act: -0.0002

Data Index: 666042 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0974. Min Act: -0.0002

Data Index: 357539 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1085632 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0978. Min Act: -0.0002

Data Index: 850812 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0870. Min Act: -0.0002

Data Index: 792074 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0915. Min Act: -0.0002

Data Index: 902402 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0984. Min Act: -0.0002

Data Index: 768511 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0800. Min Act: -0.0002

Data Index: 673847 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0859. Min Act: -0.0002

Data Index: 639857 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0975. Min Act: -0.0002

Data Index: 167763 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0803. Min Act: -0.0002

Data Index: 841448 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0861. Min Act: -0.0002

Data Index: 586504 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0816. Min Act: -0.0002

Data Index: 706277 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0743. Min Act: -0.0002

Data Index: 817645 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1316671 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0983. Min Act: -0.0002

Data Index: 656765 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0931. Min Act: -0.0002

Data Index: 941024 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0843. Min Act: -0.0002

Data Index: 488124 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0847. Min Act: -0.0002

Data Index: 458045 (C4 (Web Text))

Max Activating Token Index: 23