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

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

Neuron 2674 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1377848 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1597581 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1375395 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1487369 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1517321 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1423754 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1465782 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1475833 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1424038 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1513830 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1503068 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1409008 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1600833 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1643589 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1581816 (Python Code)

Max Activating Token Index: 396

Text #15

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1502782 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1539867 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1435247 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1391414 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1489140 (Python Code)

Max Activating Token Index: 323