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

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

Neuron 1333 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0002

Data Index: 118805 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0875. Min Act: -0.0003

Data Index: 437110 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1350458 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0889. Min Act: -0.0003

Data Index: 954642 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0896. Min Act: -0.0003

Data Index: 1323821 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0871. Min Act: -0.0002

Data Index: 231306 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0867. Min Act: -0.0002

Data Index: 899128 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0890. Min Act: -0.0002

Data Index: 48066 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0828. Min Act: -0.0002

Data Index: 808461 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0850. Min Act: -0.0003

Data Index: 477009 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0884. Min Act: -0.0003

Data Index: 402940 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0846. Min Act: -0.0002

Data Index: 466500 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0878. Min Act: -0.0002

Data Index: 242475 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1130355 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0819. Min Act: -0.0002

Data Index: 433718 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0820. Min Act: -0.0002

Data Index: 245212 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0787. Min Act: -0.0003

Data Index: 662057 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0781. Min Act: -0.0002

Data Index: 557040 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0801. Min Act: -0.0003

Data Index: 717905 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0802. Min Act: -0.0002

Data Index: 389966 (C4 (Web Text))

Max Activating Token Index: 814