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

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

Neuron 658 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.1023. Min Act: -0.0000

Data Index: 1419796 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.7503. Min Act: -0.0000

Data Index: 1580805 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1578559 (Python Code)

Max Activating Token Index: 262

Text #3

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.2801. Min Act: -0.0000

Data Index: 1488921 (Python Code)

Max Activating Token Index: 1002

Text #4

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.0802. Min Act: -0.0000

Data Index: 1572120 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.0297. Min Act: -0.0000

Data Index: 1522684 (Python Code)

Max Activating Token Index: 534

Text #6

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.1258. Min Act: -0.0000

Data Index: 1473260 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.0172. Min Act: -0.0000

Data Index: 1556453 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1535784 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.8286. Min Act: 0.0000

Data Index: 1428261 (Python Code)

Max Activating Token Index: 708

Text #10

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.9339. Min Act: -0.0000

Data Index: 1549936 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.1426. Min Act: -0.0000

Data Index: 1435520 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.0252. Min Act: 0.0000

Data Index: 1650748 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.8976. Min Act: -0.0000

Data Index: 1475919 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.8729. Min Act: -0.0000

Data Index: 1444859 (Python Code)

Max Activating Token Index: 574

Text #15

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.8689. Min Act: -0.0000

Data Index: 1586879 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.7571. Min Act: -0.0000

Data Index: 1399260 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.8586. Min Act: -0.0000

Data Index: 1636072 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.8705. Min Act: -0.0000

Data Index: 1537395 (Python Code)

Max Activating Token Index: 964

Text #19

Max Range: 3.1023. Min Range: -3.1023

Max Act: 1.7763. Min Act: -0.0000

Data Index: 1405347 (Python Code)

Max Activating Token Index: 946