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

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

Neuron 4012 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.7493. Min Act: -0.0000

Data Index: 1420311 (Python Code)

Max Activating Token Index: 118

Text #1

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.8170. Min Act: -0.0000

Data Index: 1629669 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1631219 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1475655 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.3149. Min Act: 0.0000

Data Index: 1583795 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.3623. Min Act: -0.0000

Data Index: 1493049 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1631652 (Python Code)

Max Activating Token Index: 563

Text #7

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2520. Min Act: 0.0000

Data Index: 1377359 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1366079 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1535021 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1644715 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1592700 (Python Code)

Max Activating Token Index: 708

Text #12

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.3077. Min Act: -0.0000

Data Index: 1591165 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2294. Min Act: 0.0000

Data Index: 1445679 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1396865 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1420684 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2003. Min Act: -0.0000

Data Index: 1479365 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1515910 (Python Code)

Max Activating Token Index: 188

Text #18

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1907. Min Act: 0.0000

Data Index: 1454957 (Python Code)

Max Activating Token Index: 184

Text #19

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1474752 (Python Code)

Max Activating Token Index: 894