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

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

Neuron 2954 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1547029 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1473302 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1619244 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1638985 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1561756 (Python Code)

Max Activating Token Index: 152

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1415097 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0217. Min Act: -0.0002

Data Index: 160979 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1621416 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0201. Min Act: -0.0002

Data Index: 306635 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0202. Min Act: -0.0002

Data Index: 131634 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1052883 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1507255 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1203702 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1361675 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1581430 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0177. Min Act: -0.0002

Data Index: 304721 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0174. Min Act: -0.0002

Data Index: 440217 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1156628 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1176070 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0174. Min Act: -0.0002

Data Index: 239904 (C4 (Web Text))

Max Activating Token Index: 264