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

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

Neuron 5016 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1536. Min Act: -0.0002

Data Index: 1536053 (Python Code)

Max Activating Token Index: 841

Text #1

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1277. Min Act: -0.0002

Data Index: 1560418 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1068. Min Act: -0.0002

Data Index: 1439081 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1219. Min Act: -0.0002

Data Index: 1476607 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1139. Min Act: -0.0002

Data Index: 1385090 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0954. Min Act: -0.0002

Data Index: 1438077 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0982. Min Act: -0.0002

Data Index: 1482834 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1052. Min Act: -0.0002

Data Index: 1437785 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1001. Min Act: -0.0002

Data Index: 1488986 (Python Code)

Max Activating Token Index: 789

Text #9

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0828. Min Act: -0.0002

Data Index: 1410955 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0776. Min Act: -0.0002

Data Index: 1386879 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0950. Min Act: -0.0002

Data Index: 1588353 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0934. Min Act: -0.0002

Data Index: 1413676 (Python Code)

Max Activating Token Index: 187

Text #13

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0741. Min Act: -0.0002

Data Index: 1515251 (Python Code)

Max Activating Token Index: 34

Text #14

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0743. Min Act: -0.0002

Data Index: 1446458 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0607. Min Act: -0.0002

Data Index: 1456653 (Python Code)

Max Activating Token Index: 268

Text #16

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0720. Min Act: -0.0002

Data Index: 1550317 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0722. Min Act: -0.0002

Data Index: 1528139 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0718. Min Act: -0.0002

Data Index: 1382505 (Python Code)

Max Activating Token Index: 810

Text #19

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0678. Min Act: -0.0002

Data Index: 1403990 (Python Code)

Max Activating Token Index: 763