Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1275697 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0796. Min Act: -0.0002

Data Index: 209710 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0790. Min Act: -0.0002

Data Index: 994300 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0721. Min Act: -0.0002

Data Index: 355927 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0704. Min Act: -0.0002

Data Index: 736476 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0730. Min Act: -0.0002

Data Index: 743013 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0691. Min Act: -0.0002

Data Index: 483250 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0712. Min Act: -0.0002

Data Index: 246004 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1253515 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0698. Min Act: -0.0002

Data Index: 710498 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0685. Min Act: -0.0002

Data Index: 25675 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0662. Min Act: -0.0002

Data Index: 838439 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1284335 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1286257 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0648. Min Act: -0.0002

Data Index: 942251 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1017413 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0612. Min Act: -0.0002

Data Index: 546855 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0633. Min Act: -0.0002

Data Index: 58547 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0606. Min Act: -0.0002

Data Index: 274559 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0600. Min Act: -0.0002

Data Index: 450932 (C4 (Web Text))

Max Activating Token Index: 282