Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 16 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0728. Min Act: -0.0002

Data Index: 338312 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0002

Data Index: 729006 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0727. Min Act: -0.0002

Data Index: 711859 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1218297 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1172257 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0718. Min Act: -0.0002

Data Index: 660890 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1347030 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0700. Min Act: -0.0002

Data Index: 8489 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0699. Min Act: -0.0002

Data Index: 160245 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0692. Min Act: -0.0002

Data Index: 51903 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0706. Min Act: -0.0002

Data Index: 238210 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1313506 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1311822 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0670. Min Act: -0.0002

Data Index: 17094 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0676. Min Act: -0.0002

Data Index: 715419 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0697. Min Act: -0.0002

Data Index: 109124 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0669. Min Act: -0.0002

Data Index: 890200 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0682. Min Act: -0.0003

Data Index: 825258 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0640. Min Act: -0.0002

Data Index: 117193 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0642. Min Act: -0.0002

Data Index: 179761 (C4 (Web Text))

Max Activating Token Index: 161