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

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

Neuron 5267 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3451. Min Act: -0.0000

Data Index: 733344 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3436. Min Act: -0.0000

Data Index: 585628 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3304. Min Act: -0.0000

Data Index: 635270 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3044. Min Act: -0.0000

Data Index: 552080 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2672. Min Act: -0.0000

Data Index: 796282 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1038403 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1329066 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1925. Min Act: -0.0000

Data Index: 768513 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1053152 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1028135 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1399874 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1829. Min Act: -0.0000

Data Index: 764834 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1323976 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1287044 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1807. Min Act: -0.0000

Data Index: 897495 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1612. Min Act: -0.0000

Data Index: 141215 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1566. Min Act: -0.0000

Data Index: 940118 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1588. Min Act: -0.0000

Data Index: 633455 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1783. Min Act: -0.0000

Data Index: 289804 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1590. Min Act: -0.0000

Data Index: 356734 (C4 (Web Text))

Max Activating Token Index: 907