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

Dataset: The Pile

Neuron 3641 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: 1.0634. Min Range: -1.0634

Max Act: 1.0634. Min Act: -0.0000

Data Index: 348818 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1168284 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1275048 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.4328. Min Act: -0.0000

Data Index: 486724 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1116818 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1767340 (The Pile)

Max Activating Token Index: 37

Text #6

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3864. Min Act: -0.0000

Data Index: 775092 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1758814 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1645608 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1654002 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3255. Min Act: -0.0000

Data Index: 668266 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.2617. Min Act: -0.0000

Data Index: 224621 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1550048 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1693248 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.2589. Min Act: -0.0000

Data Index: 417636 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1994085 (The Pile)

Max Activating Token Index: 359

Text #16

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1028317 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1188133 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.2997. Min Act: -0.0000

Data Index: 888479 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.1908. Min Act: -0.0000

Data Index: 613520 (The Pile)

Max Activating Token Index: 613