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

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

Neuron 3515 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3754. Min Range: -4.3754

Max Act: 4.3754. Min Act: -0.0000

Data Index: 1373646 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 4.3754. Min Range: -4.3754

Max Act: 4.0225. Min Act: -0.0000

Data Index: 1379431 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.5978. Min Act: -0.0000

Data Index: 1608445 (Python Code)

Max Activating Token Index: 441

Text #3

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.5888. Min Act: -0.0000

Data Index: 1445952 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.7329. Min Act: -0.0000

Data Index: 1573364 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.5012. Min Act: -0.0000

Data Index: 1555903 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.1805. Min Act: -0.0000

Data Index: 1557228 (Python Code)

Max Activating Token Index: 988

Text #7

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.1903. Min Act: -0.0000

Data Index: 1430809 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.5051. Min Act: -0.0000

Data Index: 1429949 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.3226. Min Act: -0.0000

Data Index: 1392641 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.1287. Min Act: -0.0000

Data Index: 1390468 (Python Code)

Max Activating Token Index: 783

Text #11

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.0116. Min Act: -0.0000

Data Index: 1368728 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.0655. Min Act: -0.0000

Data Index: 1455079 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.1906. Min Act: -0.0000

Data Index: 1548370 (Python Code)

Max Activating Token Index: 729

Text #14

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.4626. Min Act: -0.0000

Data Index: 1561099 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.1779. Min Act: -0.0000

Data Index: 1452379 (Python Code)

Max Activating Token Index: 133

Text #16

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.1244. Min Act: -0.0000

Data Index: 1584573 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.0658. Min Act: -0.0000

Data Index: 1475247 (Python Code)

Max Activating Token Index: 941

Text #18

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.0633. Min Act: -0.0001

Data Index: 1637445 (Python Code)

Max Activating Token Index: 863

Text #19

Max Range: 4.3754. Min Range: -4.3754

Max Act: 3.2069. Min Act: -0.0001

Data Index: 1638602 (Python Code)

Max Activating Token Index: 721