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

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

Neuron 4400 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: 0.0785. Min Range: -0.0785

Max Act: 0.0692. Min Act: -0.0002

Data Index: 732558 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0002

Data Index: 205099 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0762. Min Act: -0.0002

Data Index: 193433 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1049944 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0760. Min Act: -0.0002

Data Index: 733939 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0705. Min Act: -0.0002

Data Index: 90802 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0725. Min Act: -0.0002

Data Index: 557530 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0720. Min Act: -0.0002

Data Index: 43712 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0694. Min Act: -0.0002

Data Index: 200569 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0669. Min Act: -0.0002

Data Index: 888136 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0640. Min Act: -0.0002

Data Index: 544113 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1038950 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1109731 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0705. Min Act: -0.0002

Data Index: 856870 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0668. Min Act: -0.0002

Data Index: 836991 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0751. Min Act: -0.0002

Data Index: 281118 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0721. Min Act: -0.0002

Data Index: 155415 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1217169 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0699. Min Act: -0.0002

Data Index: 653139 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0700. Min Act: -0.0002

Data Index: 982319 (C4 (Web Text))

Max Activating Token Index: 360