Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 437 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3381. Min Act: -0.0001

Data Index: 1569255 (Python Code)

Max Activating Token Index: 325

Text #1

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2642. Min Act: -0.0001

Data Index: 1506219 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1579081 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1591221 (Python Code)

Max Activating Token Index: 562

Text #4

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2027. Min Act: -0.0001

Data Index: 1651208 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2352. Min Act: -0.0001

Data Index: 1387842 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1380901 (Python Code)

Max Activating Token Index: 517

Text #7

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2221. Min Act: -0.0001

Data Index: 1495187 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2007. Min Act: -0.0001

Data Index: 1603365 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1001. Min Act: -0.0001

Data Index: 1461518 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1530698 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1525389 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0856. Min Act: -0.0001

Data Index: 1532484 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0783. Min Act: -0.0001

Data Index: 1383097 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1438. Min Act: -0.0001

Data Index: 1454345 (Python Code)

Max Activating Token Index: 110

Text #15

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1404558 (Python Code)

Max Activating Token Index: 119

Text #16

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0976. Min Act: -0.0001

Data Index: 1454620 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1280. Min Act: -0.0001

Data Index: 1535352 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1597227 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0939. Min Act: -0.0001

Data Index: 1376519 (Python Code)

Max Activating Token Index: 610