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

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

Neuron 1254 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: 0.0984. Min Range: -0.0984

Max Act: 0.0984. Min Act: -0.0003

Data Index: 337694 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0831. Min Act: -0.0003

Data Index: 986294 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0840. Min Act: -0.0003

Data Index: 468063 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0841. Min Act: -0.0003

Data Index: 616143 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0834. Min Act: -0.0003

Data Index: 671453 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0798. Min Act: -0.0003

Data Index: 630641 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0758. Min Act: -0.0003

Data Index: 79001 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0703. Min Act: -0.0003

Data Index: 607575 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0723. Min Act: -0.0003

Data Index: 709422 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1257639 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0758. Min Act: -0.0003

Data Index: 330767 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0736. Min Act: -0.0003

Data Index: 375620 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0718. Min Act: -0.0003

Data Index: 337807 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1195109 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0732. Min Act: -0.0003

Data Index: 241033 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0709. Min Act: -0.0003

Data Index: 345123 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1095307 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0704. Min Act: -0.0003

Data Index: 1119956 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1229734 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1198124 (C4 (Web Text))

Max Activating Token Index: 872