Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1377 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0883. Min Act: -0.0003

Data Index: 203645 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0793. Min Act: -0.0003

Data Index: 589106 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0823. Min Act: -0.0003

Data Index: 382077 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0866. Min Act: -0.0003

Data Index: 430384 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0810. Min Act: -0.0004

Data Index: 98978 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0803. Min Act: -0.0003

Data Index: 550407 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0762. Min Act: -0.0003

Data Index: 977439 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0755. Min Act: -0.0003

Data Index: 912705 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0772. Min Act: -0.0004

Data Index: 885142 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0770. Min Act: -0.0003

Data Index: 39207 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0806. Min Act: -0.0003

Data Index: 532438 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0771. Min Act: -0.0004

Data Index: 1060894 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0733. Min Act: -0.0003

Data Index: 981682 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0767. Min Act: -0.0003

Data Index: 844894 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0754. Min Act: -0.0003

Data Index: 229889 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0776. Min Act: -0.0003

Data Index: 561818 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1036809 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1233991 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0738. Min Act: -0.0003

Data Index: 394910 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0748. Min Act: -0.0003

Data Index: 946093 (C4 (Web Text))

Max Activating Token Index: 763