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

Dataset: The Pile

Neuron 3124 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2805. Min Act: -0.0000

Data Index: 942098 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2585. Min Act: -0.0000

Data Index: 684347 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1341839 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1964. Min Act: -0.0000

Data Index: 552605 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1529541 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1056693 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1907. Min Act: -0.0000

Data Index: 874443 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1773623 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1854. Min Act: -0.0000

Data Index: 902103 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1889. Min Act: -0.0000

Data Index: 793106 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1873. Min Act: 0.0000

Data Index: 35926 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1786. Min Act: 0.0000

Data Index: 1272527 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1834. Min Act: -0.0000

Data Index: 23219 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1624939 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1909693 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1740. Min Act: -0.0000

Data Index: 895012 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1709551 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1698. Min Act: -0.0000

Data Index: 627679 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1128194 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1669528 (The Pile)

Max Activating Token Index: 937