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

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

Neuron 7 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: 0.0991. Min Range: -0.0991

Max Act: 0.0991. Min Act: -0.0002

Data Index: 874860 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0873. Min Act: -0.0002

Data Index: 430608 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0872. Min Act: -0.0002

Data Index: 187112 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0853. Min Act: -0.0002

Data Index: 490974 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0794. Min Act: -0.0002

Data Index: 120534 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0723. Min Act: -0.0002

Data Index: 35071 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0791. Min Act: -0.0002

Data Index: 663943 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0779. Min Act: -0.0002

Data Index: 431488 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0784. Min Act: -0.0002

Data Index: 761876 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1253528 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0802. Min Act: -0.0002

Data Index: 843919 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0809. Min Act: -0.0002

Data Index: 223897 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1120322 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0643. Min Act: -0.0002

Data Index: 640691 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0722. Min Act: -0.0002

Data Index: 400543 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0754. Min Act: -0.0002

Data Index: 483064 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0761. Min Act: -0.0002

Data Index: 833201 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0757. Min Act: -0.0002

Data Index: 287049 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0726. Min Act: -0.0002

Data Index: 236518 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0730. Min Act: -0.0002

Data Index: 717828 (C4 (Web Text))

Max Activating Token Index: 503