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

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

Neuron 2019 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: 1.5193. Min Range: -1.5193

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1648058 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1652724 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.5101. Min Act: -0.0000

Data Index: 1486755 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.4267. Min Act: -0.0000

Data Index: 1640108 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1454893 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1533599 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.4600. Min Act: -0.0000

Data Index: 1651268 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1518194 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1451478 (Python Code)

Max Activating Token Index: 199

Text #9

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1391375 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1570496 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1644681 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1434693 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1424226 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1484792 (Python Code)

Max Activating Token Index: 956

Text #15

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1385086 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1559039 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1561133 (Python Code)

Max Activating Token Index: 514

Text #18

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1651257 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1613279 (Python Code)

Max Activating Token Index: 399