Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1319080 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1227886 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6768. Min Act: -0.0000

Data Index: 577922 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1897973 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1250579 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6579. Min Act: -0.0001

Data Index: 24778 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5841. Min Act: -0.0000

Data Index: 175063 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5908. Min Act: -0.0000

Data Index: 686708 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1110640 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6074. Min Act: -0.0000

Data Index: 92094 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5673. Min Act: -0.0000

Data Index: 512257 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5780. Min Act: -0.0000

Data Index: 546284 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5772. Min Act: -0.0000

Data Index: 883115 (The Pile)

Max Activating Token Index: 571

Text #13

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6112. Min Act: -0.0000

Data Index: 867036 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6114. Min Act: -0.0000

Data Index: 695273 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1068501 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1174531 (The Pile)

Max Activating Token Index: 4

Text #17

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5496. Min Act: -0.0000

Data Index: 786848 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1012546 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5415. Min Act: -0.0000

Data Index: 951533 (The Pile)

Max Activating Token Index: 726