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

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

Neuron 39 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: 0.4822. Min Range: -0.4822

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1368117 (Python Code)

Max Activating Token Index: 239

Text #1

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1526329 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1602377 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1630126 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1404737 (Python Code)

Max Activating Token Index: 975

Text #5

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1442959 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1603579 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1624575 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1410505 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1500333 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1607829 (Python Code)

Max Activating Token Index: 599

Text #11

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1434392 (Python Code)

Max Activating Token Index: 504

Text #12

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1638555 (Python Code)

Max Activating Token Index: 550

Text #13

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1428805 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1614450 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1585872 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1404728 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1373557 (Python Code)

Max Activating Token Index: 499

Text #18

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1638873 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1427509 (Python Code)

Max Activating Token Index: 666