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

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

Neuron 3735 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: 1.5662. Min Range: -1.5662

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1620985 (Python Code)

Max Activating Token Index: 959

Text #1

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1466072 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.3997. Min Act: -0.0000

Data Index: 1614326 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1379276 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1409931 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1451292 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2730. Min Act: -0.0000

Data Index: 1446179 (Python Code)

Max Activating Token Index: 523

Text #7

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.3383. Min Act: -0.0000

Data Index: 1461135 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1633271 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1461237 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2911. Min Act: -0.0000

Data Index: 1480973 (Python Code)

Max Activating Token Index: 142

Text #11

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2197. Min Act: -0.0000

Data Index: 1590492 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1502795 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1551886 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1641298 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1482. Min Act: -0.0000

Data Index: 1457987 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1644752 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1588094 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1489322 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1435588 (Python Code)

Max Activating Token Index: 850