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

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

Neuron 671 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0004

Data Index: 1118852 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0833. Min Act: -0.0004

Data Index: 1172241 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0798. Min Act: -0.0004

Data Index: 582413 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0718. Min Act: -0.0004

Data Index: 1084581 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0720. Min Act: -0.0004

Data Index: 524995 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0682. Min Act: -0.0004

Data Index: 466131 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0645. Min Act: -0.0004

Data Index: 992631 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0748. Min Act: -0.0004

Data Index: 1104665 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0714. Min Act: -0.0004

Data Index: 194438 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0706. Min Act: -0.0004

Data Index: 1309178 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0649. Min Act: -0.0004

Data Index: 884959 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0695. Min Act: -0.0004

Data Index: 124270 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0691. Min Act: -0.0004

Data Index: 560619 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0654. Min Act: -0.0004

Data Index: 878181 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0643. Min Act: -0.0004

Data Index: 1132121 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0699. Min Act: -0.0004

Data Index: 163152 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0591. Min Act: -0.0004

Data Index: 733711 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0696. Min Act: -0.0004

Data Index: 327009 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0587. Min Act: -0.0004

Data Index: 1087853 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0680. Min Act: -0.0004

Data Index: 844762 (C4 (Web Text))

Max Activating Token Index: 872