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

Dataset: The Pile

Neuron 4211 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2837. Min Act: -0.0000

Data Index: 219378 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1491708 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1451120 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1409748 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2359. Min Act: -0.0000

Data Index: 495205 (The Pile)

Max Activating Token Index: 638

Text #5

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2116. Min Act: -0.0000

Data Index: 684778 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2114. Min Act: -0.0000

Data Index: 890794 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1994. Min Act: -0.0000

Data Index: 954877 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1956347 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1022792 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2090. Min Act: -0.0000

Data Index: 488085 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1775. Min Act: -0.0000

Data Index: 813005 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1935. Min Act: -0.0000

Data Index: 380696 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1860. Min Act: -0.0000

Data Index: 412006 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1727896 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1911. Min Act: -0.0000

Data Index: 128774 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1921875 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1756. Min Act: -0.0000

Data Index: 633101 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1734245 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1910. Min Act: -0.0000

Data Index: 662029 (The Pile)

Max Activating Token Index: 1020