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

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

Neuron 691 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: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1032566 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1215531 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0725. Min Act: -0.0003

Data Index: 391117 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0722. Min Act: -0.0003

Data Index: 697624 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1356605 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0663. Min Act: -0.0003

Data Index: 486622 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0723. Min Act: -0.0003

Data Index: 84436 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0701. Min Act: -0.0003

Data Index: 499083 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1038966 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0678. Min Act: -0.0003

Data Index: 708447 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0676. Min Act: -0.0003

Data Index: 257699 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0673. Min Act: -0.0003

Data Index: 615411 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1289650 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0640. Min Act: -0.0003

Data Index: 971375 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1318261 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0587. Min Act: -0.0003

Data Index: 973516 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1322147 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0623. Min Act: -0.0003

Data Index: 221076 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0613. Min Act: -0.0003

Data Index: 772578 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0621. Min Act: -0.0003

Data Index: 790629 (C4 (Web Text))

Max Activating Token Index: 835