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

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

Neuron 269 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1578732 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1447997 (Python Code)

Max Activating Token Index: 763

Text #2

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1404600 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1606265 (Python Code)

Max Activating Token Index: 199

Text #4

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1360401 (Python Code)

Max Activating Token Index: 954

Text #5

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1633011 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1597851 (Python Code)

Max Activating Token Index: 838

Text #7

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1376079 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1584901 (Python Code)

Max Activating Token Index: 419

Text #9

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1421497 (Python Code)

Max Activating Token Index: 390

Text #10

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1647837 (Python Code)

Max Activating Token Index: 295

Text #11

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1376220 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1528269 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1611471 (Python Code)

Max Activating Token Index: 705

Text #14

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1431870 (Python Code)

Max Activating Token Index: 449

Text #15

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1477471 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.6750. Min Act: -0.0000

Data Index: 562966 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.7397. Min Act: -0.0000

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1392075 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.6485. Min Act: -0.0000

Data Index: 140596 (C4 (Web Text))

Max Activating Token Index: 885