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

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

Neuron 6130 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1467250 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1472833 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1651015 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1496789 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1614839 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1370866 (Python Code)

Max Activating Token Index: 748

Text #6

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1499126 (Python Code)

Max Activating Token Index: 932

Text #7

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1647393 (Python Code)

Max Activating Token Index: 883

Text #8

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1638324 (Python Code)

Max Activating Token Index: 974

Text #9

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1625509 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1471562 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1586118 (Python Code)

Max Activating Token Index: 790

Text #12

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1549247 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1489435 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1372580 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1481782 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1381387 (Python Code)

Max Activating Token Index: 970

Text #17

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1640001 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1517821 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1592967 (Python Code)

Max Activating Token Index: 1010