Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3761 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1241548 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1842537 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1385916 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1680375 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1635591 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1238256 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1969866 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1174400 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.4727. Min Act: -0.0000

Data Index: 879573 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1758454 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1035964 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5114. Min Act: -0.0000

Data Index: 111728 (The Pile)

Max Activating Token Index: 36

Text #12

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5249. Min Act: -0.0000

Data Index: 813548 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5199. Min Act: -0.0000

Data Index: 947033 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.4954. Min Act: -0.0000

Data Index: 28086 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.4531. Min Act: -0.0000

Data Index: 496239 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1142048 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5219. Min Act: -0.0000

Data Index: 560164 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.4823. Min Act: -0.0000

Data Index: 17469 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1875060 (The Pile)

Max Activating Token Index: 505