Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 519 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0003

Data Index: 77419 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0731. Min Act: -0.0002

Data Index: 676585 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0728. Min Act: -0.0004

Data Index: 769118 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0684. Min Act: -0.0003

Data Index: 424022 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0707. Min Act: -0.0004

Data Index: 548125 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1343294 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0726. Min Act: -0.0003

Data Index: 676599 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1149825 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1305551 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0678. Min Act: -0.0004

Data Index: 975041 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0672. Min Act: -0.0004

Data Index: 1013799 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0685. Min Act: -0.0003

Data Index: 93473 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0682. Min Act: -0.0004

Data Index: 734998 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1241866 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1051795 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0680. Min Act: -0.0003

Data Index: 635136 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0677. Min Act: -0.0003

Data Index: 978937 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0638. Min Act: -0.0004

Data Index: 323399 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0679. Min Act: -0.0003

Data Index: 304636 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0669. Min Act: -0.0003

Data Index: 583102 (C4 (Web Text))

Max Activating Token Index: 111