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

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

Neuron 2328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1536218 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1424646 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1392742 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1471972 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6225. Min Act: -0.0001

Data Index: 1464267 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1512181 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1364807 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6782. Min Act: -0.0001

Data Index: 1542829 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1549265 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1418310 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1401905 (Python Code)

Max Activating Token Index: 738

Text #11

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1609016 (Python Code)

Max Activating Token Index: 864

Text #12

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1562663 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1630454 (Python Code)

Max Activating Token Index: 700

Text #14

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1414848 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1395168 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5558. Min Act: -0.0001

Data Index: 1610383 (Python Code)

Max Activating Token Index: 626

Text #17

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1576604 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1583080 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1614303 (Python Code)

Max Activating Token Index: 239