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

Dataset: The Pile

Neuron 2098 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.8603. Min Act: -0.0000

Data Index: 728594 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7934. Min Act: -0.0000

Data Index: 1050108 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7904. Min Act: -0.0000

Data Index: 1777019 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7458. Min Act: -0.0000

Data Index: 727789 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7434. Min Act: -0.0000

Data Index: 375063 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5134. Min Act: -0.0000

Data Index: 960521 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.6030. Min Act: -0.0000

Data Index: 876420 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.6939. Min Act: -0.0000

Data Index: 859999 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.6810. Min Act: -0.0000

Data Index: 1821094 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7805. Min Act: -0.0000

Data Index: 1103674 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7700. Min Act: -0.0000

Data Index: 231649 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1017938 (The Pile)

Max Activating Token Index: 626

Text #12

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5487. Min Act: -0.0000

Data Index: 613494 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.6258. Min Act: -0.0000

Data Index: 839129 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.6079. Min Act: -0.0000

Data Index: 743058 (The Pile)

Max Activating Token Index: 880

Text #15

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7188. Min Act: -0.0000

Data Index: 565294 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5304. Min Act: -0.0000

Data Index: 283069 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1603691 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4238. Min Act: -0.0000

Data Index: 1962935 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.6019. Min Act: -0.0000

Data Index: 85973 (The Pile)

Max Activating Token Index: 447