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

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

Neuron 4330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.8261. Min Act: -0.0000

Data Index: 1335222 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.8269. Min Act: -0.0000

Data Index: 1074782 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.4766. Min Act: -0.0000

Data Index: 1020339 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.5739. Min Act: -0.0000

Data Index: 914079 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.4421. Min Act: -0.0000

Data Index: 1034185 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.4001. Min Act: -0.0000

Data Index: 755574 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.2106. Min Act: -0.0000

Data Index: 993792 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.2878. Min Act: -0.0000

Data Index: 273895 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.1819. Min Act: -0.0000

Data Index: 682696 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.1300. Min Act: -0.0000

Data Index: 230142 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.1212. Min Act: -0.0000

Data Index: 133295 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.2373. Min Act: -0.0000

Data Index: 503988 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.1892. Min Act: -0.0000

Data Index: 1359361 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.2842. Min Act: -0.0000

Data Index: 900602 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.0392. Min Act: -0.0000

Data Index: 1095601 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.1614. Min Act: -0.0000

Data Index: 1298771 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.1403. Min Act: -0.0000

Data Index: 225178 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.1373. Min Act: -0.0000

Data Index: 935404 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.2322. Min Act: -0.0000

Data Index: 1102723 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 2.8269. Min Range: -2.8269

Max Act: 2.2247. Min Act: -0.0000

Data Index: 1091551 (C4 (Web Text))

Max Activating Token Index: 845