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

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

Neuron 413 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1470701 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1611179 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1632339 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8824. Min Act: -0.0000

Data Index: 462235 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1556053 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1216149 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1477644 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8413. Min Act: -0.0000

Data Index: 444824 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9226. Min Act: -0.0000

Data Index: 301426 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1452448 (Python Code)

Max Activating Token Index: 694

Text #10

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1362596 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1646998 (Python Code)

Max Activating Token Index: 1009

Text #12

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8170. Min Act: -0.0000

Data Index: 598176 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1467500 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8294. Min Act: -0.0000

Data Index: 459725 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.7377. Min Act: -0.0000

Data Index: 708253 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1211218 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1588279 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8234. Min Act: -0.0000

Data Index: 325037 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1090385 (C4 (Web Text))

Max Activating Token Index: 36