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

Dataset: The Pile

Neuron 2761 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1555225 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2027. Min Act: -0.0000

Data Index: 795599 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1170507 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1497222 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1587744 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1033965 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1918. Min Act: -0.0000

Data Index: 191004 (The Pile)

Max Activating Token Index: 679

Text #7

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1913. Min Act: -0.0000

Data Index: 776139 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1413883 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1837. Min Act: -0.0000

Data Index: 965843 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1874. Min Act: -0.0000

Data Index: 942064 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1905546 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1374098 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1438193 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1109074 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1759. Min Act: -0.0000

Data Index: 201729 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1378209 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1729. Min Act: -0.0000

Data Index: 558699 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1674. Min Act: -0.0000

Data Index: 968867 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1444231 (The Pile)

Max Activating Token Index: 559