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

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

Neuron 2207 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0003

Data Index: 111801 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0820. Min Act: -0.0003

Data Index: 998634 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1200668 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0777. Min Act: -0.0003

Data Index: 131122 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0761. Min Act: -0.0003

Data Index: 126098 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0819. Min Act: -0.0003

Data Index: 103391 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0778. Min Act: -0.0003

Data Index: 669868 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1219880 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0729. Min Act: -0.0003

Data Index: 8090 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0709. Min Act: -0.0002

Data Index: 84610 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1004741 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0742. Min Act: -0.0002

Data Index: 581282 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0752. Min Act: -0.0002

Data Index: 725368 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1047291 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0709. Min Act: -0.0003

Data Index: 403815 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1079834 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0718. Min Act: -0.0002

Data Index: 305743 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1217047 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0728. Min Act: -0.0003

Data Index: 594490 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0730. Min Act: -0.0002

Data Index: 230811 (C4 (Web Text))

Max Activating Token Index: 928