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

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

Neuron 3067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1553787 (Python Code)

Max Activating Token Index: 953

Text #1

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1556905 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1639413 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1564783 (Python Code)

Max Activating Token Index: 668

Text #4

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9883. Min Act: -0.0000

Data Index: 916082 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1523246 (Python Code)

Max Activating Token Index: 893

Text #6

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1532031 (Python Code)

Max Activating Token Index: 811

Text #7

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1493050 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1601384 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1399868 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1635810 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1561329 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1623367 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1498471 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1472280 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1537270 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1541740 (Python Code)

Max Activating Token Index: 591

Text #17

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1552059 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1646800 (Python Code)

Max Activating Token Index: 50

Text #19

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1575188 (Python Code)

Max Activating Token Index: 784