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

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

Neuron 1694 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1585081 (Python Code)

Max Activating Token Index: 442

Text #1

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1499352 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1596593 (Python Code)

Max Activating Token Index: 192

Text #3

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1597404 (Python Code)

Max Activating Token Index: 418

Text #4

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1468677 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1405404 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1365727 (Python Code)

Max Activating Token Index: 186

Text #7

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1574107 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1367387 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1446230 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1437964 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1652972 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1407952 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1490920 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1381556 (Python Code)

Max Activating Token Index: 46

Text #15

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1381795 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1622606 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1425953 (Python Code)

Max Activating Token Index: 891

Text #18

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1502305 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1619278 (Python Code)

Max Activating Token Index: 16