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

Dataset: The Pile

Neuron 2760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.8554. Min Act: -0.0000

Data Index: 1114590 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 5.2905. Min Range: -5.2905

Max Act: 5.0448. Min Act: -0.0000

Data Index: 1519185 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.9154. Min Act: -0.0000

Data Index: 1551047 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 5.2905. Min Range: -5.2905

Max Act: 5.2905. Min Act: -0.0000

Data Index: 413094 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 5.2905. Min Range: -5.2905

Max Act: 5.0758. Min Act: -0.0000

Data Index: 1500326 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.9973. Min Act: -0.0000

Data Index: 594305 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.8558. Min Act: -0.0000

Data Index: 399859 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.8957. Min Act: -0.0000

Data Index: 1863990 (The Pile)

Max Activating Token Index: 246

Text #8

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.7968. Min Act: -0.0000

Data Index: 313760 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.9888. Min Act: -0.0000

Data Index: 816759 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.7899. Min Act: -0.0000

Data Index: 443453 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 5.2905. Min Range: -5.2905

Max Act: 5.1826. Min Act: -0.0000

Data Index: 1340444 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.9048. Min Act: -0.0000

Data Index: 1179310 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.9136. Min Act: -0.0000

Data Index: 481237 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.9590. Min Act: -0.0000

Data Index: 1376552 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.9681. Min Act: -0.0000

Data Index: 312777 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 5.2905. Min Range: -5.2905

Max Act: 5.2552. Min Act: -0.0000

Data Index: 915045 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.5450. Min Act: -0.0000

Data Index: 808026 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.6889. Min Act: -0.0000

Data Index: 870223 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 5.2905. Min Range: -5.2905

Max Act: 4.8437. Min Act: -0.0000

Data Index: 139373 (The Pile)

Max Activating Token Index: 186