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

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

Neuron 5345 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4900. Min Act: -0.0001

Data Index: 1248058 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1261658 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1048695 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3865. Min Act: -0.0000

Data Index: 532953 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3386. Min Act: -0.0001

Data Index: 1607775 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3295. Min Act: -0.0001

Data Index: 1091113 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1349765 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1601844 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1147536 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1167110 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3178. Min Act: -0.0000

Data Index: 705697 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1384820 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2908. Min Act: -0.0000

Data Index: 591585 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1461333 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1381340 (Python Code)

Max Activating Token Index: 368

Text #15

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2719. Min Act: -0.0000

Data Index: 570833 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1440597 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1605531 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1601402 (Python Code)

Max Activating Token Index: 694

Text #19

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1389305 (Python Code)

Max Activating Token Index: 201