Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1723 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5556. Min Act: -0.0002

Data Index: 1380860 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4532. Min Act: -0.0002

Data Index: 1405077 (Python Code)

Max Activating Token Index: 710

Text #2

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4811. Min Act: -0.0001

Data Index: 1423117 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4599. Min Act: 0.0001

Data Index: 1570047 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1471432 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4415. Min Act: 0.0001

Data Index: 1592679 (Python Code)

Max Activating Token Index: 530

Text #6

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4256. Min Act: 0.0001

Data Index: 1372057 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1479323 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4470. Min Act: -0.0001

Data Index: 1413733 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3993. Min Act: -0.0001

Data Index: 1394905 (Python Code)

Max Activating Token Index: 980

Text #10

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4274. Min Act: 0.0000

Data Index: 1622860 (Python Code)

Max Activating Token Index: 788

Text #11

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4274. Min Act: -0.0002

Data Index: 1587895 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1451219 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1503362 (Python Code)

Max Activating Token Index: 142

Text #14

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3484. Min Act: 0.0001

Data Index: 1598320 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3806. Min Act: 0.0001

Data Index: 1429090 (Python Code)

Max Activating Token Index: 232

Text #16

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3919. Min Act: 0.0001

Data Index: 1566130 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3711. Min Act: 0.0001

Data Index: 1534804 (Python Code)

Max Activating Token Index: 251

Text #18

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3619. Min Act: 0.0001

Data Index: 1501910 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3855. Min Act: -0.0002

Data Index: 1615310 (Python Code)

Max Activating Token Index: 356