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

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

Neuron 3467 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2677. Min Act: -0.0000

Data Index: 681415 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2465. Min Act: -0.0000

Data Index: 333702 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2193. Min Act: -0.0000

Data Index: 29516 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1464391 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2297. Min Act: -0.0000

Data Index: 730656 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2376. Min Act: -0.0000

Data Index: 317326 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2052. Min Act: -0.0000

Data Index: 36678 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1513963 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1649862 (Python Code)

Max Activating Token Index: 560

Text #9

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1878. Min Act: -0.0000

Data Index: 583182 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1852. Min Act: -0.0000

Data Index: 568581 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1957. Min Act: -0.0000

Data Index: 790312 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1061155 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1786. Min Act: -0.0000

Data Index: 201303 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1723. Min Act: -0.0000

Data Index: 716043 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1139967 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1394293 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1445. Min Act: -0.0000

Data Index: 172059 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1025930 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1826. Min Act: -0.0000

Data Index: 157377 (C4 (Web Text))

Max Activating Token Index: 93