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

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

Neuron 1739 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: 0.0638. Min Range: -0.0638

Max Act: 0.0636. Min Act: -0.0002

Data Index: 767466 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0004

Data Index: 1067837 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0632. Min Act: -0.0003

Data Index: 106425 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0633. Min Act: -0.0003

Data Index: 360598 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0624. Min Act: -0.0003

Data Index: 713048 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1211624 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0601. Min Act: -0.0003

Data Index: 438808 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0602. Min Act: -0.0003

Data Index: 971173 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1040595 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0544. Min Act: -0.0003

Data Index: 447530 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1258356 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0543. Min Act: -0.0003

Data Index: 648580 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0538. Min Act: -0.0004

Data Index: 1027299 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0537. Min Act: -0.0003

Data Index: 577684 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0521. Min Act: -0.0003

Data Index: 564100 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1334630 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0506. Min Act: -0.0003

Data Index: 245016 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0525. Min Act: -0.0003

Data Index: 210889 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0507. Min Act: -0.0003

Data Index: 199967 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1237844 (C4 (Web Text))

Max Activating Token Index: 394