Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5760 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1456560 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1524299 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1568677 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1651687 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1472109 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1428678 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1589508 (Python Code)

Max Activating Token Index: 742

Text #7

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1570343 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1625571 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1618743 (Python Code)

Max Activating Token Index: 465

Text #10

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1554856 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1592425 (Python Code)

Max Activating Token Index: 1012

Text #12

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1597959 (Python Code)

Max Activating Token Index: 982

Text #13

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1621405 (Python Code)

Max Activating Token Index: 182

Text #14

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1524280 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1492915 (Python Code)

Max Activating Token Index: 710

Text #16

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1545952 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1514285 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1563454 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 0.9834. Min Range: -0.9834

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1636298 (Python Code)

Max Activating Token Index: 935