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

Dataset: The Pile

Neuron 3691 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1059326 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0783. Min Act: -0.0000

Data Index: 744634 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1030392 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 58015 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 141722 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 201538 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 286243 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 32258 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 53088 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 31401 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 203537 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 27573 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 243054 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 78145 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 190206 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 149171 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 133952 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 239976 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 54228 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0000

Data Index: 120442 (The Pile)

Max Activating Token Index: 1