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

Dataset: The Pile

Neuron 2623 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.6653. Min Act: -0.0000

Data Index: 617921 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.6495. Min Act: -0.0000

Data Index: 253212 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1941692 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5877. Min Act: -0.0000

Data Index: 101804 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5645. Min Act: -0.0000

Data Index: 232833 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1828089 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1173200 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1949416 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1665335 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5392. Min Act: -0.0000

Data Index: 24555 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5148. Min Act: -0.0000

Data Index: 774796 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5151. Min Act: -0.0000

Data Index: 664456 (The Pile)

Max Activating Token Index: 840

Text #12

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5071. Min Act: -0.0000

Data Index: 790911 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1803361 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1697976 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1122214 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1499710 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1478070 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.4741. Min Act: -0.0000

Data Index: 319782 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.6653. Min Range: -0.6653

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1370341 (The Pile)

Max Activating Token Index: 296