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

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

Neuron 2043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7517. Min Act: -0.0000

Data Index: 1629007 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.8594. Min Act: -0.0000

Data Index: 295950 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7491. Min Act: -0.0000

Data Index: 1377655 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7794. Min Act: -0.0000

Data Index: 1490760 (Python Code)

Max Activating Token Index: 878

Text #4

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.6892. Min Act: -0.0000

Data Index: 399519 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7389. Min Act: -0.0000

Data Index: 776955 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7125. Min Act: -0.0000

Data Index: 855923 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7642. Min Act: -0.0000

Data Index: 1480834 (Python Code)

Max Activating Token Index: 863

Text #8

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1022453 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.6028. Min Act: -0.0000

Data Index: 1622806 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1230503 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.5837. Min Act: -0.0000

Data Index: 619963 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.5638. Min Act: -0.0000

Data Index: 780742 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.5707. Min Act: -0.0000

Data Index: 820365 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.5565. Min Act: -0.0000

Data Index: 398679 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.5542. Min Act: -0.0000

Data Index: 831591 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.5016. Min Act: -0.0000

Data Index: 451928 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.4020. Min Act: -0.0000

Data Index: 789402 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.4975. Min Act: -0.0000

Data Index: 884557 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.5589. Min Act: -0.0000

Data Index: 27386 (C4 (Web Text))

Max Activating Token Index: 931