Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1533 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1650612 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3200. Min Act: -0.0001

Data Index: 1563844 (Python Code)

Max Activating Token Index: 452

Text #2

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3323. Min Act: -0.0001

Data Index: 1473106 (Python Code)

Max Activating Token Index: 893

Text #3

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1396483 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1445930 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1575724 (Python Code)

Max Activating Token Index: 593

Text #6

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1425114 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1439149 (Python Code)

Max Activating Token Index: 168

Text #8

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1477586 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1629243 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1371895 (Python Code)

Max Activating Token Index: 147

Text #11

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2824. Min Act: -0.0001

Data Index: 1445959 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1577498 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1635715 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1434876 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1414319 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1600731 (Python Code)

Max Activating Token Index: 943

Text #17

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1615299 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1472941 (Python Code)

Max Activating Token Index: 416

Text #19

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2656. Min Act: -0.0001

Data Index: 1365471 (Python Code)

Max Activating Token Index: 29