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

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

Neuron 708 in Layer 0

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: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1584775 (Python Code)

Max Activating Token Index: 834

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1461269 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1371776 (Python Code)

Max Activating Token Index: 545

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1467050 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1384926 (Python Code)

Max Activating Token Index: 604

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1631525 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1510548 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1562730 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1441012 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1617369 (Python Code)

Max Activating Token Index: 312

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1396936 (Python Code)

Max Activating Token Index: 872

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1490832 (Python Code)

Max Activating Token Index: 821

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1459533 (Python Code)

Max Activating Token Index: 828

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1363261 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1519933 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1541193 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1501271 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1470582 (Python Code)

Max Activating Token Index: 991

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1564032 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1565112 (Python Code)

Max Activating Token Index: 5