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

Dataset: The Pile

Neuron 3462 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1930688 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.9098. Min Act: -0.0000

Data Index: 901393 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8273. Min Act: -0.0000

Data Index: 825237 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1130119 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1139073 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8196. Min Act: -0.0000

Data Index: 774544 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8101. Min Act: -0.0000

Data Index: 343500 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1569920 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7057. Min Act: -0.0000

Data Index: 352825 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1862322 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1004143 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1404353 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8446. Min Act: -0.0000

Data Index: 313541 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1812319 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7280. Min Act: -0.0000

Data Index: 261607 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1116908 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1004435 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1797602 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7219. Min Act: -0.0000

Data Index: 637312 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1207321 (The Pile)

Max Activating Token Index: 367