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

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

Neuron 2517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.8809. Min Act: -0.0000

Data Index: 1641267 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.8102. Min Act: -0.0000

Data Index: 1568401 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1129941 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.4966. Min Act: -0.0000

Data Index: 678897 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1294490 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.6141. Min Act: -0.0000

Data Index: 571067 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.5116. Min Act: -0.0000

Data Index: 678368 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1633185 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1321584 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.4636. Min Act: -0.0000

Data Index: 1553760 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.3974. Min Act: -0.0000

Data Index: 156315 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.2611. Min Act: -0.0000

Data Index: 752422 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.3825. Min Act: -0.0000

Data Index: 1377573 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.4821. Min Act: -0.0000

Data Index: 1334720 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.3947. Min Act: -0.0000

Data Index: 1599472 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1444398 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1496209 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.2853. Min Act: -0.0000

Data Index: 234114 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1449863 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1439341 (Python Code)

Max Activating Token Index: 1018