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

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

Neuron 2915 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.6106. Min Act: -0.0000

Data Index: 1473096 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.0797. Min Act: -0.0000

Data Index: 1535451 (Python Code)

Max Activating Token Index: 689

Text #2

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.1434. Min Act: -0.0000

Data Index: 1412937 (Python Code)

Max Activating Token Index: 978

Text #3

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.0249. Min Act: -0.0000

Data Index: 1522794 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.1149. Min Act: -0.0000

Data Index: 1580680 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.8140. Min Act: -0.0000

Data Index: 1515468 (Python Code)

Max Activating Token Index: 486

Text #6

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.4805. Min Act: -0.0000

Data Index: 1606542 (Python Code)

Max Activating Token Index: 732

Text #7

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.5509. Min Act: -0.0000

Data Index: 1583920 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.2652. Min Act: -0.0000

Data Index: 1557395 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.3817. Min Act: -0.0000

Data Index: 1537754 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.1928. Min Act: -0.0000

Data Index: 1615404 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.0971. Min Act: -0.0000

Data Index: 1547875 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 4.6106. Min Range: -4.6106

Max Act: 3.2548. Min Act: -0.0000

Data Index: 1400314 (Python Code)

Max Activating Token Index: 475

Text #13

Max Range: 4.6106. Min Range: -4.6106

Max Act: 2.9226. Min Act: -0.0000

Data Index: 1420584 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 4.6106. Min Range: -4.6106

Max Act: 2.7579. Min Act: -0.0000

Data Index: 1620210 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 4.6106. Min Range: -4.6106

Max Act: 2.9973. Min Act: -0.0000

Data Index: 1642261 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 4.6106. Min Range: -4.6106

Max Act: 2.7551. Min Act: -0.0000

Data Index: 1609652 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 4.6106. Min Range: -4.6106

Max Act: 2.6048. Min Act: -0.0000

Data Index: 1648926 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 4.6106. Min Range: -4.6106

Max Act: 2.8539. Min Act: -0.0000

Data Index: 1373714 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 4.6106. Min Range: -4.6106

Max Act: 2.5011. Min Act: -0.0000

Data Index: 1641273 (Python Code)

Max Activating Token Index: 887