Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1006 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0003

Data Index: 558108 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0711. Min Act: -0.0003

Data Index: 916588 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1060735 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0650. Min Act: -0.0002

Data Index: 798047 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0637. Min Act: -0.0003

Data Index: 308940 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1233748 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0623. Min Act: -0.0003

Data Index: 207086 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0583. Min Act: -0.0003

Data Index: 45925 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0596. Min Act: -0.0003

Data Index: 891093 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0617. Min Act: -0.0003

Data Index: 659614 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1130193 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0577. Min Act: -0.0003

Data Index: 746325 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1246575 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0561. Min Act: -0.0003

Data Index: 322554 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0592. Min Act: -0.0002

Data Index: 851355 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1093970 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0595. Min Act: -0.0002

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0518. Min Act: -0.0003

Data Index: 411364 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1167596 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0575. Min Act: -0.0003

Data Index: 591824 (C4 (Web Text))

Max Activating Token Index: 570