Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 191 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0703. Min Act: -0.0003

Data Index: 755626 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0003

Data Index: 788489 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1235728 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0692. Min Act: -0.0003

Data Index: 749758 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0679. Min Act: -0.0003

Data Index: 662195 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0678. Min Act: -0.0003

Data Index: 371542 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1226729 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0668. Min Act: -0.0003

Data Index: 626846 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1029730 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0657. Min Act: -0.0003

Data Index: 507308 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0652. Min Act: -0.0003

Data Index: 950255 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0640. Min Act: -0.0003

Data Index: 199607 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0644. Min Act: -0.0003

Data Index: 552649 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0654. Min Act: -0.0004

Data Index: 1018743 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0616. Min Act: -0.0003

Data Index: 22039 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0625. Min Act: -0.0003

Data Index: 683106 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0590. Min Act: -0.0003

Data Index: 75466 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0611. Min Act: -0.0003

Data Index: 929918 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0608. Min Act: -0.0003

Data Index: 881886 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0595. Min Act: -0.0003

Data Index: 978046 (C4 (Web Text))

Max Activating Token Index: 24