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

Dataset: The Pile

Neuron 2278 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1077770 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1393. Min Act: -0.0000

Data Index: 576750 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1412566 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1480427 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1750940 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1093. Min Act: -0.0000

Data Index: 669227 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1342029 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1251323 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1078. Min Act: -0.0000

Data Index: 749674 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1077. Min Act: -0.0000

Data Index: 227985 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1014. Min Act: -0.0000

Data Index: 964338 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1066. Min Act: -0.0000

Data Index: 445960 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1451117 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1467540 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1031. Min Act: -0.0000

Data Index: 702292 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1060. Min Act: -0.0000

Data Index: 17473 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1569920 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.1018. Min Act: -0.0000

Data Index: 608072 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.0941. Min Act: -0.0000

Data Index: 333020 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.1454. Min Range: -0.1454

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1069801 (The Pile)

Max Activating Token Index: 156