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

Dataset: The Pile

Neuron 841 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: 0.9152. Min Range: -0.9152

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1125782 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7475. Min Act: -0.0000

Data Index: 195114 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6141. Min Act: -0.0000

Data Index: 702499 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1986305 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1032703 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1019122 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5627. Min Act: -0.0000

Data Index: 207519 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5217. Min Act: -0.0000

Data Index: 256654 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1848743 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1027108 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1331337 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1223602 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.4978. Min Act: -0.0000

Data Index: 182682 (The Pile)

Max Activating Token Index: 709

Text #13

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5083. Min Act: -0.0000

Data Index: 534084 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5102. Min Act: -0.0000

Data Index: 239247 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1130405 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.4712. Min Act: -0.0000

Data Index: 742768 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.4686. Min Act: -0.0000

Data Index: 828492 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.4985. Min Act: -0.0000

Data Index: 958556 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1751156 (The Pile)

Max Activating Token Index: 78