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

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

Neuron 4598 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: 0.7983. Min Range: -0.7983

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1568513 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1495842 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1587636 (Python Code)

Max Activating Token Index: 700

Text #3

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1398905 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1572113 (Python Code)

Max Activating Token Index: 904

Text #5

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1596422 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1621486 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1511319 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1424481 (Python Code)

Max Activating Token Index: 569

Text #9

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1481857 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1642696 (Python Code)

Max Activating Token Index: 225

Text #11

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1368509 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1536339 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1400151 (Python Code)

Max Activating Token Index: 435

Text #14

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1614712 (Python Code)

Max Activating Token Index: 767

Text #15

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1414231 (Python Code)

Max Activating Token Index: 420

Text #16

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1558882 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5465. Min Act: -0.0000

Data Index: 513250 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1395855 (Python Code)

Max Activating Token Index: 907

Text #19

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1105901 (C4 (Web Text))

Max Activating Token Index: 34