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

Dataset: The Pile

Neuron 4452 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1097. Min Range: -5.1097

Max Act: 5.1097. Min Act: -0.0000

Data Index: 1118270 (The Pile)

Max Activating Token Index: 969

Text #1

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.6856. Min Act: -0.0000

Data Index: 1381705 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7668. Min Act: -0.0000

Data Index: 354938 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.5067. Min Act: -0.0000

Data Index: 521934 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.4228. Min Act: -0.0000

Data Index: 1935576 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.5604. Min Act: -0.0000

Data Index: 1898976 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.1796. Min Act: -0.0000

Data Index: 1510138 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.1849. Min Act: -0.0000

Data Index: 1801374 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.1391. Min Act: -0.0000

Data Index: 92303 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.0315. Min Act: -0.0000

Data Index: 56447 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.9348. Min Act: -0.0000

Data Index: 1103509 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.8826. Min Act: -0.0000

Data Index: 1883726 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.8858. Min Act: -0.0000

Data Index: 789114 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.7030. Min Act: -0.0000

Data Index: 1310873 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.8773. Min Act: -0.0000

Data Index: 1058271 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.0089. Min Act: -0.0000

Data Index: 1037669 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.8353. Min Act: -0.0000

Data Index: 1990732 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.8163. Min Act: -0.0000

Data Index: 882075 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.6695. Min Act: -0.0000

Data Index: 1006579 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 5.1097. Min Range: -5.1097

Max Act: 3.7895. Min Act: -0.0000

Data Index: 161802 (The Pile)

Max Activating Token Index: 1015