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

Dataset: The Pile

Neuron 457 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: 0.7660. Min Range: -0.7660

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1992837 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7304. Min Act: -0.0000

Data Index: 736677 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1664461 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6664. Min Act: -0.0000

Data Index: 268360 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1349815 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7101. Min Act: -0.0000

Data Index: 677451 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6856. Min Act: -0.0000

Data Index: 794804 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6419. Min Act: -0.0000

Data Index: 637177 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6132. Min Act: -0.0000

Data Index: 712346 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1308525 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5754. Min Act: -0.0000

Data Index: 565199 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6017. Min Act: -0.0000

Data Index: 291109 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1849434 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1920165 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6276. Min Act: -0.0000

Data Index: 6047 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1140412 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1978281 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1755328 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5920. Min Act: -0.0000

Data Index: 217586 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5929. Min Act: -0.0000

Data Index: 867681 (The Pile)

Max Activating Token Index: 482