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

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

Neuron 1036 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1556400 (Python Code)

Max Activating Token Index: 618

Text #1

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1427553 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1647573 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1598385 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1504495 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1564179 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1449965 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1362617 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1430700 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1118745 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4754. Min Act: -0.0000

Data Index: 945979 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4954. Min Act: -0.0000

Data Index: 130582 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1635044 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4921. Min Act: -0.0000

Data Index: 106653 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4898. Min Act: -0.0000

Data Index: 634156 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1521721 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1344370 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1488455 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1375846 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.4121. Min Act: -0.0000

Data Index: 723195 (C4 (Web Text))

Max Activating Token Index: 743