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

Dataset: The Pile

Neuron 4584 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.5739. Min Act: -0.0000

Data Index: 989295 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.2063. Min Act: -0.0000

Data Index: 146507 (The Pile)

Max Activating Token Index: 937

Text #2

Max Range: 4.5739. Min Range: -4.5739

Max Act: 4.0739. Min Act: -0.0000

Data Index: 385761 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.9853. Min Act: -0.0000

Data Index: 868687 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.4638. Min Act: -0.0000

Data Index: 877248 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.4871. Min Act: -0.0000

Data Index: 1615676 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.6333. Min Act: -0.0000

Data Index: 35889 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.6753. Min Act: -0.0000

Data Index: 1344653 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.5837. Min Act: -0.0000

Data Index: 1500905 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.7375. Min Act: -0.0000

Data Index: 489582 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.7683. Min Act: -0.0000

Data Index: 318492 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.3749. Min Act: -0.0000

Data Index: 1245244 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.3066. Min Act: -0.0000

Data Index: 675088 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.3985. Min Act: -0.0000

Data Index: 402793 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.5663. Min Act: -0.0000

Data Index: 1936076 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.5698. Min Act: -0.0000

Data Index: 28956 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.5576. Min Act: -0.0000

Data Index: 1783080 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.5425. Min Act: -0.0000

Data Index: 1295636 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.1554. Min Act: -0.0000

Data Index: 593271 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 4.5739. Min Range: -4.5739

Max Act: 3.4709. Min Act: -0.0000

Data Index: 1095887 (The Pile)

Max Activating Token Index: 129