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

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

Neuron 1391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.3781. Min Act: -0.0000

Data Index: 131819 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.2403. Min Act: -0.0000

Data Index: 466059 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1315911 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1054991 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1126184 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0202. Min Act: -0.0000

Data Index: 966008 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1110651 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9607. Min Act: -0.0000

Data Index: 679795 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1076456 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0258. Min Act: -0.0000

Data Index: 684459 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1212813 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.8625. Min Act: -0.0000

Data Index: 213615 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1270067 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1120049 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9017. Min Act: -0.0000

Data Index: 772365 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.8438. Min Act: -0.0000

Data Index: 330454 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.8627. Min Act: -0.0000

Data Index: 531740 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.8812. Min Act: -0.0000

Data Index: 757240 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.8561. Min Act: -0.0000

Data Index: 390761 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.7753. Min Act: -0.0000

Data Index: 854882 (C4 (Web Text))

Max Activating Token Index: 301