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

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

Neuron 4379 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: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1145964 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1125276 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0725. Min Act: -0.0002

Data Index: 465805 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1134898 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1344120 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0542. Min Act: -0.0002

Data Index: 437529 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1110049 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1358311 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0642. Min Act: -0.0002

Data Index: 678938 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1295038 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1091266 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0709. Min Act: -0.0002

Data Index: 140184 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1070438 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1177736 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0583. Min Act: -0.0002

Data Index: 389760 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0603. Min Act: -0.0002

Data Index: 620190 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0624. Min Act: -0.0002

Data Index: 499232 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0596. Min Act: -0.0002

Data Index: 123817 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0560. Min Act: -0.0002

Data Index: 400546 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1288713 (C4 (Web Text))

Max Activating Token Index: 511