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

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

Neuron 2362 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7453. Min Act: -0.0001

Data Index: 1178233 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7487. Min Act: -0.0001

Data Index: 1353277 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7494. Min Act: -0.0001

Data Index: 288975 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7966. Min Act: -0.0001

Data Index: 991845 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7216. Min Act: -0.0001

Data Index: 616118 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7226. Min Act: -0.0001

Data Index: 1344890 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7193. Min Act: -0.0001

Data Index: 979711 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1161989 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6949. Min Act: -0.0001

Data Index: 740442 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6793. Min Act: -0.0001

Data Index: 27883 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6987. Min Act: -0.0001

Data Index: 842701 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6983. Min Act: -0.0001

Data Index: 1269250 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6778. Min Act: -0.0001

Data Index: 739816 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6804. Min Act: -0.0001

Data Index: 1265695 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6739. Min Act: -0.0001

Data Index: 1035325 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6928. Min Act: -0.0001

Data Index: 273844 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5930. Min Act: -0.0001

Data Index: 829185 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6425. Min Act: -0.0001

Data Index: 673130 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6586. Min Act: -0.0001

Data Index: 627543 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6511. Min Act: -0.0001

Data Index: 1278238 (C4 (Web Text))

Max Activating Token Index: 395