Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 382 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9996. Min Act: -0.0001

Data Index: 1363827 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1556918 (Python Code)

Max Activating Token Index: 1000

Text #2

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9375. Min Act: -0.0000

Data Index: 1593816 (Python Code)

Max Activating Token Index: 405

Text #3

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9279. Min Act: -0.0001

Data Index: 1590150 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7715. Min Act: -0.0001

Data Index: 1474684 (Python Code)

Max Activating Token Index: 1006

Text #5

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.8649. Min Act: -0.0001

Data Index: 1591687 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7304. Min Act: -0.0001

Data Index: 1477749 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6695. Min Act: -0.0001

Data Index: 1400431 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7103. Min Act: -0.0000

Data Index: 1635790 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5657. Min Act: -0.0001

Data Index: 1629313 (Python Code)

Max Activating Token Index: 891

Text #10

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6550. Min Act: -0.0001

Data Index: 1479153 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6701. Min Act: -0.0001

Data Index: 1606550 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1638973 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.8785. Min Act: -0.0001

Data Index: 1510970 (Python Code)

Max Activating Token Index: 554

Text #14

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1363046 (Python Code)

Max Activating Token Index: 584

Text #15

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5896. Min Act: -0.0001

Data Index: 1621246 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5704. Min Act: 0.0000

Data Index: 1620694 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4463. Min Act: -0.0001

Data Index: 1597178 (Python Code)

Max Activating Token Index: 995

Text #18

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7550. Min Act: -0.0001

Data Index: 1402623 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4279. Min Act: -0.0001

Data Index: 1490957 (Python Code)

Max Activating Token Index: 224