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

Dataset: The Pile

Neuron 3374 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1235787 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1415416 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4859. Min Act: -0.0000

Data Index: 384159 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4850. Min Act: -0.0000

Data Index: 118257 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4873. Min Act: -0.0000

Data Index: 458230 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1754277 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1171451 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1508973 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4645. Min Act: -0.0000

Data Index: 2706 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1158505 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1184562 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1793254 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1333724 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1889398 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4097. Min Act: -0.0000

Data Index: 573971 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.3960. Min Act: -0.0000

Data Index: 417907 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1674021 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4025. Min Act: -0.0000

Data Index: 474105 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.4076. Min Act: -0.0000

Data Index: 618245 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 0.6944. Min Range: -0.6944

Max Act: 0.3826. Min Act: -0.0000

Data Index: 493324 (The Pile)

Max Activating Token Index: 833