Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1982 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.9624. Min Act: -0.0001

Data Index: 520747 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1606658 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.7285. Min Act: -0.0001

Data Index: 1419264 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.7717. Min Act: -0.0000

Data Index: 936738 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.7510. Min Act: -0.0001

Data Index: 562738 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1484361 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1548918 (Python Code)

Max Activating Token Index: 854

Text #7

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1171936 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1426076 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5728. Min Act: 0.0001

Data Index: 1554305 (Python Code)

Max Activating Token Index: 920

Text #10

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.6084. Min Act: 0.0002

Data Index: 1525502 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5998. Min Act: 0.0001

Data Index: 1639372 (Python Code)

Max Activating Token Index: 959

Text #12

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1423724 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.6056. Min Act: -0.0001

Data Index: 243860 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5937. Min Act: -0.0001

Data Index: 164510 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5594. Min Act: 0.0001

Data Index: 1592988 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5970. Min Act: 0.0000

Data Index: 1463667 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5768. Min Act: -0.0001

Data Index: 403988 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5902. Min Act: 0.0000

Data Index: 1529720 (Python Code)

Max Activating Token Index: 1006

Text #19

Max Range: 0.9624. Min Range: -0.9624

Max Act: 0.5495. Min Act: -0.0001

Data Index: 410190 (C4 (Web Text))

Max Activating Token Index: 264