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

Dataset: The Pile

Neuron 752 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: 0.7446. Min Range: -0.7446

Max Act: 0.7446. Min Act: -0.0000

Data Index: 340070 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6924. Min Act: -0.0000

Data Index: 390396 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6785. Min Act: -0.0000

Data Index: 363321 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6588. Min Act: -0.0000

Data Index: 30527 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1922834 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6411. Min Act: -0.0000

Data Index: 244102 (The Pile)

Max Activating Token Index: 881

Text #6

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6051. Min Act: -0.0000

Data Index: 54376 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1387876 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1669722 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6244. Min Act: -0.0000

Data Index: 645918 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6040. Min Act: -0.0000

Data Index: 195227 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1086576 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6005. Min Act: -0.0000

Data Index: 333373 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1512740 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1213629 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1416313 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5951. Min Act: -0.0000

Data Index: 355327 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1877444 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1118920 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1212938 (The Pile)

Max Activating Token Index: 24