Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3769 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1453926 (Python Code)

Max Activating Token Index: 194

Text #1

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1565604 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1614652 (Python Code)

Max Activating Token Index: 839

Text #3

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.7888. Min Act: -0.0000

Data Index: 886665 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1566049 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1369890 (Python Code)

Max Activating Token Index: 553

Text #6

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.7456. Min Act: -0.0000

Data Index: 379139 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1557564 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1363433 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1566159 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1466187 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1390246 (Python Code)

Max Activating Token Index: 834

Text #12

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1473371 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1541257 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1377054 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6411. Min Act: -0.0000

Data Index: 406576 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1503836 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6691. Min Act: -0.0000

Data Index: 431352 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1509329 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 0.9398. Min Range: -0.9398

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1525879 (Python Code)

Max Activating Token Index: 887