Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 319 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0003

Data Index: 848521 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0765. Min Act: -0.0003

Data Index: 28935 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0743. Min Act: -0.0003

Data Index: 721239 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0741. Min Act: -0.0003

Data Index: 301308 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0729. Min Act: -0.0003

Data Index: 491789 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0707. Min Act: -0.0003

Data Index: 334109 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0699. Min Act: -0.0003

Data Index: 474608 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0738. Min Act: -0.0003

Data Index: 500880 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0683. Min Act: -0.0003

Data Index: 8159 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0733. Min Act: -0.0003

Data Index: 691651 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0716. Min Act: -0.0003

Data Index: 740809 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1217275 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0650. Min Act: -0.0003

Data Index: 312393 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0685. Min Act: -0.0003

Data Index: 812400 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0670. Min Act: -0.0003

Data Index: 816315 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0683. Min Act: -0.0003

Data Index: 667702 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0695. Min Act: -0.0003

Data Index: 820483 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0667. Min Act: -0.0003

Data Index: 633715 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0691. Min Act: -0.0003

Data Index: 857412 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0661. Min Act: -0.0003

Data Index: 182754 (C4 (Web Text))

Max Activating Token Index: 86