Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2172 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9742. Min Act: -0.0003

Data Index: 237426 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9821. Min Act: -0.0002

Data Index: 948737 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9449. Min Act: -0.0002

Data Index: 1323661 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9191. Min Act: -0.0002

Data Index: 39936 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9027. Min Act: -0.0002

Data Index: 680022 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9383. Min Act: -0.0003

Data Index: 311999 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9042. Min Act: -0.0002

Data Index: 924114 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9186. Min Act: -0.0002

Data Index: 709299 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9102. Min Act: -0.0002

Data Index: 1122982 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9064. Min Act: -0.0002

Data Index: 872164 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9012. Min Act: -0.0002

Data Index: 238645 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8889. Min Act: -0.0003

Data Index: 350835 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8914. Min Act: -0.0002

Data Index: 569629 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8635. Min Act: -0.0003

Data Index: 839222 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8702. Min Act: -0.0002

Data Index: 411346 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8524. Min Act: -0.0002

Data Index: 109336 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8446. Min Act: -0.0002

Data Index: 922434 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8603. Min Act: -0.0003

Data Index: 1002559 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8536. Min Act: -0.0002

Data Index: 911509 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8501. Min Act: -0.0002

Data Index: 1120673 (C4 (Web Text))

Max Activating Token Index: 476