Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1276 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0002

Data Index: 90992 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1120630 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0681. Min Act: -0.0002

Data Index: 11114 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0602. Min Act: -0.0002

Data Index: 653527 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0669. Min Act: -0.0002

Data Index: 545064 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1217913 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0688. Min Act: -0.0002

Data Index: 742781 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1281795 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0634. Min Act: -0.0002

Data Index: 925293 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0629. Min Act: -0.0002

Data Index: 202592 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1302229 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1056445 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0610. Min Act: -0.0002

Data Index: 849635 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0605. Min Act: -0.0002

Data Index: 821100 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0597. Min Act: -0.0002

Data Index: 219161 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0590. Min Act: -0.0001

Data Index: 791739 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0600. Min Act: -0.0002

Data Index: 748031 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0552. Min Act: -0.0002

Data Index: 913318 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1227908 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1266009 (C4 (Web Text))

Max Activating Token Index: 206