Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3650 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0953. Min Act: -0.0002

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1048334 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0887. Min Act: -0.0003

Data Index: 1032343 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0874. Min Act: -0.0003

Data Index: 1121073 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0863. Min Act: -0.0002

Data Index: 162302 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0895. Min Act: -0.0003

Data Index: 31614 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1237677 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0836. Min Act: -0.0002

Data Index: 557185 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0824. Min Act: -0.0002

Data Index: 861378 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0819. Min Act: -0.0002

Data Index: 62818 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0801. Min Act: -0.0002

Data Index: 722338 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0773. Min Act: -0.0002

Data Index: 870179 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0769. Min Act: -0.0002

Data Index: 624287 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0748. Min Act: -0.0002

Data Index: 852126 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0762. Min Act: -0.0002

Data Index: 833999 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1233509 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0754. Min Act: -0.0002

Data Index: 682888 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0752. Min Act: -0.0002

Data Index: 596184 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0751. Min Act: -0.0002

Data Index: 109965 (C4 (Web Text))

Max Activating Token Index: 671