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

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

Neuron 1579 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.7248. Min Act: -0.0000

Data Index: 961909 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6594. Min Act: -0.0000

Data Index: 973664 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1416083 (Python Code)

Max Activating Token Index: 516

Text #3

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1424156 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1435369 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6163. Min Act: -0.0000

Data Index: 766634 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1539592 (Python Code)

Max Activating Token Index: 344

Text #7

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5023. Min Act: -0.0000

Data Index: 905882 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1385142 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1646544 (Python Code)

Max Activating Token Index: 233

Text #10

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5250. Min Act: -0.0000

Data Index: 998306 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1419997 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1445058 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1592681 (Python Code)

Max Activating Token Index: 626

Text #14

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5317. Min Act: -0.0000

Data Index: 812481 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1445635 (Python Code)

Max Activating Token Index: 829

Text #16

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5269. Min Act: -0.0000

Data Index: 402197 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1381264 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1622725 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1557219 (Python Code)

Max Activating Token Index: 160