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

Dataset: The Pile

Neuron 565 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: 1.4794. Min Range: -1.4794

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1149849 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1448705 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1429573 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.4794. Min Act: -0.0000

Data Index: 170223 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1033422 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.4334. Min Act: -0.0000

Data Index: 1248803 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.3746. Min Act: -0.0000

Data Index: 680064 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1611898 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1326163 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.3286. Min Act: -0.0000

Data Index: 771448 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.3026. Min Act: -0.0000

Data Index: 529015 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.4668. Min Act: -0.0000

Data Index: 1897796 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1921387 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1965214 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1093245 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.1446. Min Act: -0.0000

Data Index: 1077723 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.2594. Min Act: -0.0000

Data Index: 152116 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.2711. Min Act: -0.0000

Data Index: 49633 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.1123. Min Act: -0.0000

Data Index: 707893 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 1.4794. Min Range: -1.4794

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1113439 (The Pile)

Max Activating Token Index: 156