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

Dataset: The Pile

Neuron 3994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.9413. Min Act: -0.0000

Data Index: 111113 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.8712. Min Act: -0.0000

Data Index: 273678 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1847480 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1208276 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1401211 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.8125. Min Act: -0.0000

Data Index: 839166 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6744. Min Act: -0.0000

Data Index: 49995 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6695. Min Act: -0.0000

Data Index: 975448 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1165979 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1972643 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1456523 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7126. Min Act: -0.0000

Data Index: 760488 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6706. Min Act: -0.0000

Data Index: 336272 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6661. Min Act: -0.0000

Data Index: 855493 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6468. Min Act: -0.0000

Data Index: 855214 (The Pile)

Max Activating Token Index: 553

Text #15

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7328. Min Act: -0.0000

Data Index: 415896 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1171817 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1205966 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1042395 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1270754 (The Pile)

Max Activating Token Index: 440