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

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

Neuron 1999 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0973. Min Act: -0.0003

Data Index: 695090 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0919. Min Act: -0.0003

Data Index: 837879 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0785. Min Act: -0.0003

Data Index: 357959 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0851. Min Act: -0.0003

Data Index: 1001347 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0832. Min Act: -0.0003

Data Index: 513650 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0773. Min Act: -0.0003

Data Index: 156268 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0850. Min Act: -0.0003

Data Index: 562149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1066876 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1264634 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0807. Min Act: -0.0003

Data Index: 704728 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0799. Min Act: -0.0003

Data Index: 719589 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0795. Min Act: -0.0003

Data Index: 1020810 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0791. Min Act: -0.0003

Data Index: 804586 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0699. Min Act: -0.0003

Data Index: 646140 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0751. Min Act: -0.0003

Data Index: 698516 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0722. Min Act: -0.0003

Data Index: 639931 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0694. Min Act: -0.0003

Data Index: 781872 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0755. Min Act: -0.0003

Data Index: 406429 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0725. Min Act: -0.0003

Data Index: 153391 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1018481 (C4 (Web Text))

Max Activating Token Index: 662