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

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

Neuron 1461 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1571055 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1392160 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1497895 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1609918 (Python Code)

Max Activating Token Index: 231

Text #4

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1498728 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1366773 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1479632 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1596719 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1437117 (Python Code)

Max Activating Token Index: 435

Text #9

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1560364 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1568553 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1587283 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1578934 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1599528 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1512636 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1400530 (Python Code)

Max Activating Token Index: 280

Text #16

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1513041 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1629535 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1583154 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 0.9113. Min Range: -0.9113

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1500219 (Python Code)

Max Activating Token Index: 94