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

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

Neuron 1514 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: 3.5492. Min Range: -3.5492

Max Act: 3.5348. Min Act: -0.0000

Data Index: 1643125 (Python Code)

Max Activating Token Index: 909

Text #1

Max Range: 3.5492. Min Range: -3.5492

Max Act: 3.5492. Min Act: -0.0000

Data Index: 1498604 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 3.5492. Min Range: -3.5492

Max Act: 3.1532. Min Act: -0.0000

Data Index: 1384194 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 3.5492. Min Range: -3.5492

Max Act: 3.0461. Min Act: -0.0000

Data Index: 1511078 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 3.5492. Min Range: -3.5492

Max Act: 3.0617. Min Act: -0.0000

Data Index: 1444257 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.6159. Min Act: -0.0000

Data Index: 1398996 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.8200. Min Act: -0.0000

Data Index: 1434009 (Python Code)

Max Activating Token Index: 475

Text #7

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.6497. Min Act: -0.0000

Data Index: 1418823 (Python Code)

Max Activating Token Index: 355

Text #8

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.7926. Min Act: -0.0000

Data Index: 1417814 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.6389. Min Act: -0.0000

Data Index: 1380087 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.7800. Min Act: 0.0000

Data Index: 1618242 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.7836. Min Act: -0.0000

Data Index: 1508635 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.6401. Min Act: -0.0000

Data Index: 1585402 (Python Code)

Max Activating Token Index: 113

Text #13

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.7597. Min Act: -0.0000

Data Index: 1556448 (Python Code)

Max Activating Token Index: 865

Text #14

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.4905. Min Act: -0.0000

Data Index: 1401140 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.8420. Min Act: -0.0000

Data Index: 1412496 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.5648. Min Act: -0.0000

Data Index: 1503172 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.6644. Min Act: -0.0000

Data Index: 1588295 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.5690. Min Act: -0.0000

Data Index: 1608789 (Python Code)

Max Activating Token Index: 762

Text #19

Max Range: 3.5492. Min Range: -3.5492

Max Act: 2.5342. Min Act: -0.0000

Data Index: 1366742 (Python Code)

Max Activating Token Index: 855