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

Dataset: The Pile

Neuron 3263 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: 0.4683. Min Range: -0.4683

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1574033 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4513. Min Act: -0.0000

Data Index: 900052 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1359697 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4112. Min Act: -0.0000

Data Index: 230058 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1592994 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4093. Min Act: -0.0000

Data Index: 354512 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1471923 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1920714 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1457931 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3842. Min Act: -0.0000

Data Index: 727763 (The Pile)

Max Activating Token Index: 844

Text #10

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4085. Min Act: -0.0000

Data Index: 111937 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1003887 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3851. Min Act: -0.0000

Data Index: 264917 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3842. Min Act: -0.0000

Data Index: 916650 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3759. Min Act: -0.0000

Data Index: 177015 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1310073 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1032468 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1875821 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3984. Min Act: -0.0000

Data Index: 907081 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1943679 (The Pile)

Max Activating Token Index: 188