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

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

Neuron 3694 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8665. Min Act: -0.0003

Data Index: 212472 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8870. Min Act: -0.0003

Data Index: 897860 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.9152. Min Act: -0.0003

Data Index: 906839 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.0376. Min Range: -1.0376

Max Act: 1.0376. Min Act: -0.0003

Data Index: 273060 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7979. Min Act: -0.0003

Data Index: 403208 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7736. Min Act: -0.0003

Data Index: 1553222 (Python Code)

Max Activating Token Index: 764

Text #6

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8359. Min Act: -0.0003

Data Index: 963959 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8068. Min Act: -0.0003

Data Index: 657887 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8239. Min Act: -0.0003

Data Index: 1323400 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7953. Min Act: -0.0003

Data Index: 452593 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8978. Min Act: -0.0003

Data Index: 677956 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8415. Min Act: -0.0003

Data Index: 618455 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7401. Min Act: -0.0003

Data Index: 1114477 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8344. Min Act: -0.0003

Data Index: 1115038 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7802. Min Act: -0.0003

Data Index: 865932 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.9129. Min Act: -0.0003

Data Index: 9329 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8072. Min Act: -0.0003

Data Index: 439498 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8295. Min Act: -0.0003

Data Index: 229592 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8844. Min Act: -0.0003

Data Index: 875951 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8284. Min Act: -0.0003

Data Index: 63409 (C4 (Web Text))

Max Activating Token Index: 460