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

Dataset: The Pile

Neuron 2159 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: 1.4392. Min Range: -1.4392

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1172441 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.4114. Min Act: -0.0000

Data Index: 449616 (The Pile)

Max Activating Token Index: 378

Text #2

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2551. Min Act: -0.0000

Data Index: 1806138 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1665835 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2827. Min Act: -0.0000

Data Index: 602358 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2739. Min Act: -0.0000

Data Index: 880503 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2060. Min Act: -0.0000

Data Index: 1976354 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1356234 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1556. Min Act: -0.0000

Data Index: 863689 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1016247 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1789537 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0425. Min Act: -0.0000

Data Index: 415009 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1840755 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1858209 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0739. Min Act: -0.0000

Data Index: 756108 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0270. Min Act: -0.0000

Data Index: 840041 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0142. Min Act: -0.0000

Data Index: 215475 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1984616 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0953. Min Act: -0.0000

Data Index: 575427 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9418. Min Act: -0.0000

Data Index: 183357 (The Pile)

Max Activating Token Index: 144