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

Dataset: The Pile

Neuron 3601 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: 0.5640. Min Range: -0.5640

Max Act: 0.5640. Min Act: -0.0000

Data Index: 541400 (The Pile)

Max Activating Token Index: 450

Text #1

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1898854 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3839. Min Act: -0.0000

Data Index: 750786 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3456. Min Act: -0.0000

Data Index: 761604 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1095133 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1935266 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3199. Min Act: -0.0000

Data Index: 411008 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1249211 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3294. Min Act: -0.0000

Data Index: 305557 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1787990 (The Pile)

Max Activating Token Index: 402

Text #10

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3054. Min Act: -0.0000

Data Index: 362668 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1839631 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1824395 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1998741 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1818284 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1543033 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2800. Min Act: -0.0000

Data Index: 412149 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1472449 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2773. Min Act: 0.0000

Data Index: 236903 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.2684. Min Act: -0.0000

Data Index: 176538 (The Pile)

Max Activating Token Index: 252