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

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

Neuron 2930 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1480629 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1634442 (Python Code)

Max Activating Token Index: 282

Text #2

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1554945 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1496732 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1410174 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1571409 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1571093 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1535352 (Python Code)

Max Activating Token Index: 505

Text #8

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1634019 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1375301 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1618892 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1411011 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5530. Min Act: -0.0000

Data Index: 638158 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1470068 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1479683 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5572. Min Act: -0.0000

Data Index: 70592 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1601933 (Python Code)

Max Activating Token Index: 575

Text #17

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1539678 (Python Code)

Max Activating Token Index: 68

Text #18

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5714. Min Act: -0.0000

Data Index: 668974 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1575467 (Python Code)

Max Activating Token Index: 300