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

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

Neuron 5412 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1411. Min Range: -1.1411

Max Act: 1.1411. Min Act: -0.0000

Data Index: 743078 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 1.1411. Min Range: -1.1411

Max Act: 1.0856. Min Act: -0.0000

Data Index: 919296 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.1411. Min Range: -1.1411

Max Act: 1.0311. Min Act: -0.0000

Data Index: 706237 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1263584 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9415. Min Act: -0.0000

Data Index: 360649 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1514342 (Python Code)

Max Activating Token Index: 1005

Text #6

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1540836 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8489. Min Act: -0.0000

Data Index: 328269 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1617351 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9412. Min Act: -0.0000

Data Index: 557930 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1190259 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1037180 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1633831 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1503373 (Python Code)

Max Activating Token Index: 881

Text #14

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.7219. Min Act: -0.0000

Data Index: 926188 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.7090. Min Act: -0.0000

Data Index: 365003 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1132772 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1582014 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1026067 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.6693. Min Act: -0.0000

Data Index: 944561 (C4 (Web Text))

Max Activating Token Index: 571