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

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

Neuron 2018 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0885. Min Act: -0.0000

Data Index: 402074 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0767. Min Act: -0.0000

Data Index: 553412 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0734. Min Act: -0.0000

Data Index: 233728 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0761. Min Act: -0.0000

Data Index: 334765 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0731. Min Act: -0.0000

Data Index: 750918 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1654 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1069121 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0682. Min Act: -0.0000

Data Index: 384932 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0654. Min Act: -0.0000

Data Index: 273956 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0686. Min Act: -0.0000

Data Index: 355945 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0656. Min Act: -0.0000

Data Index: 866641 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0711. Min Act: -0.0000

Data Index: 206636 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1158891 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0692. Min Act: -0.0000

Data Index: 121462 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1342403 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0641. Min Act: -0.0000

Data Index: 799621 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0597. Min Act: -0.0000

Data Index: 97919 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1338312 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0701. Min Act: -0.0000

Data Index: 74816 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0662. Min Act: -0.0000

Data Index: 232185 (C4 (Web Text))

Max Activating Token Index: 790