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

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

Neuron 3593 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: 6.2750. Min Range: -6.2750

Max Act: 6.2750. Min Act: -0.0000

Data Index: 1401800 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.6732. Min Act: -0.0000

Data Index: 1438155 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.7655. Min Act: -0.0000

Data Index: 1607929 (Python Code)

Max Activating Token Index: 979

Text #3

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.6245. Min Act: -0.0000

Data Index: 1470148 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 6.2750. Min Range: -6.2750

Max Act: 4.8855. Min Act: -0.0000

Data Index: 1426631 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.3673. Min Act: -0.0000

Data Index: 1613248 (Python Code)

Max Activating Token Index: 769

Text #6

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.3651. Min Act: -0.0000

Data Index: 1479117 (Python Code)

Max Activating Token Index: 466

Text #7

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.3553. Min Act: -0.0000

Data Index: 1408907 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.3262. Min Act: -0.0000

Data Index: 1482720 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 6.2750. Min Range: -6.2750

Max Act: 4.8783. Min Act: -0.0000

Data Index: 1629900 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.2226. Min Act: -0.0000

Data Index: 1468763 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.1946. Min Act: -0.0000

Data Index: 1563666 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 6.2750. Min Range: -6.2750

Max Act: 4.9773. Min Act: -0.0000

Data Index: 1564453 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 6.2750. Min Range: -6.2750

Max Act: 4.9752. Min Act: -0.0000

Data Index: 1539834 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.1396. Min Act: -0.0000

Data Index: 1550233 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.0796. Min Act: -0.0000

Data Index: 1628891 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 6.2750. Min Range: -6.2750

Max Act: 4.9436. Min Act: -0.0000

Data Index: 1631949 (Python Code)

Max Activating Token Index: 520

Text #17

Max Range: 6.2750. Min Range: -6.2750

Max Act: 4.8572. Min Act: -0.0000

Data Index: 1475384 (Python Code)

Max Activating Token Index: 225

Text #18

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.2203. Min Act: -0.0000

Data Index: 1529524 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 6.2750. Min Range: -6.2750

Max Act: 5.1556. Min Act: -0.0000

Data Index: 1590631 (Python Code)

Max Activating Token Index: 995