Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1957 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.6354. Min Act: -0.0003

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.3215. Min Act: -0.0004

Data Index: 380521 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.3097. Min Act: -0.0003

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #3

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.2959. Min Act: -0.0003

Data Index: 54642 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.2309. Min Act: -0.0003

Data Index: 1090252 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.2586. Min Act: -0.0003

Data Index: 1575383 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.2099. Min Act: -0.0003

Data Index: 26556 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1986. Min Act: -0.0003

Data Index: 1011829 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.2026. Min Act: -0.0003

Data Index: 949737 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1902. Min Act: -0.0003

Data Index: 863864 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1850. Min Act: -0.0003

Data Index: 58598 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1837. Min Act: -0.0003

Data Index: 362588 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1752. Min Act: -0.0003

Data Index: 448653 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1845. Min Act: -0.0003

Data Index: 433352 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1807. Min Act: -0.0003

Data Index: 955248 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1818. Min Act: -0.0003

Data Index: 345143 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1693. Min Act: -0.0003

Data Index: 260311 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1676. Min Act: -0.0003

Data Index: 346301 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1612. Min Act: -0.0003

Data Index: 1304675 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.1688. Min Act: -0.0003

Data Index: 468845 (C4 (Web Text))

Max Activating Token Index: 80