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

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

Neuron 136 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: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0003

Data Index: 884180 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0683. Min Act: -0.0003

Data Index: 932540 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1109509 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1020069 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1115644 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0640. Min Act: -0.0003

Data Index: 389563 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0638. Min Act: -0.0003

Data Index: 914583 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0597. Min Act: -0.0003

Data Index: 885882 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0644. Min Act: -0.0003

Data Index: 597411 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0619. Min Act: -0.0003

Data Index: 88576 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1352956 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1217255 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0599. Min Act: -0.0003

Data Index: 207628 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0596. Min Act: -0.0003

Data Index: 613321 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0585. Min Act: -0.0004

Data Index: 901583 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0583. Min Act: -0.0002

Data Index: 841882 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0600. Min Act: -0.0003

Data Index: 733496 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0609. Min Act: -0.0003

Data Index: 880021 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1072961 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1068603 (C4 (Web Text))

Max Activating Token Index: 80