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

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

Neuron 1687 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1470617 (Python Code)

Max Activating Token Index: 885

Text #1

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1610098 (Python Code)

Max Activating Token Index: 535

Text #2

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9189. Min Act: -0.0000

Data Index: 1574393 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7083. Min Act: -0.0000

Data Index: 35770 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.8901. Min Act: -0.0000

Data Index: 1482894 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7616. Min Act: -0.0000

Data Index: 1446260 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1535064 (Python Code)

Max Activating Token Index: 194

Text #7

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5942. Min Act: -0.0000

Data Index: 862272 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7545. Min Act: -0.0000

Data Index: 1580601 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5381. Min Act: -0.0000

Data Index: 1615896 (Python Code)

Max Activating Token Index: 223

Text #10

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6390. Min Act: -0.0000

Data Index: 1340977 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5418. Min Act: -0.0000

Data Index: 1559634 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6176. Min Act: -0.0000

Data Index: 1364764 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5723. Min Act: -0.0000

Data Index: 1566924 (Python Code)

Max Activating Token Index: 183

Text #14

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1369007 (Python Code)

Max Activating Token Index: 806

Text #15

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5491. Min Act: -0.0000

Data Index: 1408694 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5506. Min Act: -0.0000

Data Index: 1500966 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5383. Min Act: -0.0000

Data Index: 1432650 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1434470 (Python Code)

Max Activating Token Index: 372

Text #19

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1412053 (Python Code)

Max Activating Token Index: 148