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

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

Neuron 2772 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.7266. Min Act: -0.0001

Data Index: 1506020 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.7116. Min Act: -0.0001

Data Index: 1656983 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.6124. Min Act: -0.0001

Data Index: 1434766 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.5411. Min Act: -0.0001

Data Index: 1637001 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4330. Min Act: -0.0001

Data Index: 1506257 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4850. Min Act: -0.0001

Data Index: 1600731 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4620. Min Act: -0.0001

Data Index: 1365372 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4188. Min Act: -0.0001

Data Index: 1480164 (Python Code)

Max Activating Token Index: 59

Text #8

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4216. Min Act: -0.0001

Data Index: 1404607 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.5429. Min Act: -0.0001

Data Index: 1576495 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4929. Min Act: -0.0001

Data Index: 1455166 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.3432. Min Act: -0.0001

Data Index: 1580681 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4235. Min Act: -0.0001

Data Index: 1643762 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.4188. Min Act: -0.0001

Data Index: 1591335 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.3610. Min Act: -0.0001

Data Index: 1414139 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.3573. Min Act: -0.0001

Data Index: 1476580 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.3953. Min Act: -0.0001

Data Index: 1573390 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.3103. Min Act: -0.0001

Data Index: 1618538 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.3736. Min Act: -0.0001

Data Index: 1447284 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 1.7266. Min Range: -1.7266

Max Act: 1.3314. Min Act: -0.0001

Data Index: 1361653 (Python Code)

Max Activating Token Index: 11