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

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

Neuron 1722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7158. Min Range: -3.7158

Max Act: 3.7158. Min Act: -0.0000

Data Index: 1452589 (Python Code)

Max Activating Token Index: 754

Text #1

Max Range: 3.7158. Min Range: -3.7158

Max Act: 3.1656. Min Act: -0.0000

Data Index: 1444890 (Python Code)

Max Activating Token Index: 457

Text #2

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.7950. Min Act: -0.0000

Data Index: 1456022 (Python Code)

Max Activating Token Index: 306

Text #3

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.8919. Min Act: -0.0000

Data Index: 1498790 (Python Code)

Max Activating Token Index: 204

Text #4

Max Range: 3.7158. Min Range: -3.7158

Max Act: 3.0228. Min Act: -0.0000

Data Index: 1457181 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.6009. Min Act: -0.0000

Data Index: 1529265 (Python Code)

Max Activating Token Index: 849

Text #6

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.6751. Min Act: -0.0000

Data Index: 1394437 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.5052. Min Act: -0.0000

Data Index: 1553738 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.6601. Min Act: -0.0000

Data Index: 1517341 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.6364. Min Act: -0.0000

Data Index: 1397214 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.7684. Min Act: -0.0000

Data Index: 1399625 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.6193. Min Act: -0.0000

Data Index: 1410047 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.5887. Min Act: -0.0000

Data Index: 1368899 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.7200. Min Act: -0.0000

Data Index: 1476042 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.5845. Min Act: -0.0000

Data Index: 1378998 (Python Code)

Max Activating Token Index: 370

Text #15

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.5714. Min Act: -0.0000

Data Index: 1502777 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.5541. Min Act: -0.0000

Data Index: 1596580 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.6547. Min Act: -0.0000

Data Index: 1611011 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.4051. Min Act: -0.0000

Data Index: 1573593 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 3.7158. Min Range: -3.7158

Max Act: 2.6305. Min Act: -0.0000

Data Index: 1497003 (Python Code)

Max Activating Token Index: 814