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

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

Neuron 1543 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0150. Min Range: -3.0150

Max Act: 3.0150. Min Act: -0.0000

Data Index: 1537768 (Python Code)

Max Activating Token Index: 583

Text #1

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.4417. Min Act: -0.0000

Data Index: 1511106 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.5805. Min Act: -0.0000

Data Index: 1651788 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.5135. Min Act: -0.0000

Data Index: 1388172 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.3681. Min Act: -0.0000

Data Index: 1402747 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.3888. Min Act: -0.0000

Data Index: 399211 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.4831. Min Act: -0.0000

Data Index: 1427380 (Python Code)

Max Activating Token Index: 446

Text #7

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.4622. Min Act: -0.0000

Data Index: 1434073 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.0875. Min Act: -0.0000

Data Index: 1484793 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 3.0150. Min Range: -3.0150

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1492489 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.1103. Min Act: -0.0000

Data Index: 1497443 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.2022. Min Act: -0.0000

Data Index: 1597586 (Python Code)

Max Activating Token Index: 232

Text #12

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.2525. Min Act: -0.0000

Data Index: 1393527 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.1287. Min Act: -0.0000

Data Index: 1648889 (Python Code)

Max Activating Token Index: 127

Text #14

Max Range: 3.0150. Min Range: -3.0150

Max Act: 1.9978. Min Act: -0.0000

Data Index: 1459290 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.2752. Min Act: -0.0000

Data Index: 1342907 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.0831. Min Act: -0.0000

Data Index: 1595603 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.1776. Min Act: -0.0000

Data Index: 1393430 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 3.0150. Min Range: -3.0150

Max Act: 1.9236. Min Act: -0.0000

Data Index: 1429753 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.0375. Min Act: -0.0000

Data Index: 1555455 (Python Code)

Max Activating Token Index: 963