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

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

Neuron 3985 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.6654. Min Act: -0.0000

Data Index: 1034103 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.6722. Min Act: -0.0000

Data Index: 1603659 (Python Code)

Max Activating Token Index: 691

Text #2

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.7307. Min Act: -0.0000

Data Index: 1585297 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.6356. Min Act: -0.0000

Data Index: 17461 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.6002. Min Act: 0.0000

Data Index: 1386979 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.4269. Min Act: 0.0000

Data Index: 1590732 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1556728 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.3820. Min Act: -0.0000

Data Index: 315605 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.4271. Min Act: -0.0000

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.3486. Min Act: -0.0000

Data Index: 1405062 (Python Code)

Max Activating Token Index: 502

Text #10

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.4134. Min Act: 0.0000

Data Index: 1410141 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.3033. Min Act: -0.0000

Data Index: 392853 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.3187. Min Act: -0.0000

Data Index: 110147 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.3073. Min Act: -0.0000

Data Index: 68797 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.3039. Min Act: -0.0000

Data Index: 576910 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1318251 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1238155 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1461833 (Python Code)

Max Activating Token Index: 677

Text #18

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.2687. Min Act: -0.0000

Data Index: 345815 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 1.7307. Min Range: -1.7307

Max Act: 1.2907. Min Act: -0.0000

Data Index: 208901 (C4 (Web Text))

Max Activating Token Index: 713