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

Dataset: The Pile

Neuron 1463 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.6875. Min Act: -0.0000

Data Index: 361070 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1951297 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3608. Min Act: -0.0000

Data Index: 347178 (The Pile)

Max Activating Token Index: 56

Text #3

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.4196. Min Act: -0.0000

Data Index: 580822 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1616333 (The Pile)

Max Activating Token Index: 57

Text #5

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.4000. Min Act: -0.0000

Data Index: 1324641 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3965. Min Act: -0.0000

Data Index: 980988 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2375. Min Act: -0.0000

Data Index: 348009 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1125951 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3334. Min Act: -0.0000

Data Index: 451931 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3569. Min Act: -0.0000

Data Index: 903074 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1640815 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3867. Min Act: -0.0000

Data Index: 993158 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2418. Min Act: -0.0000

Data Index: 515543 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1046246 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2822. Min Act: -0.0000

Data Index: 392298 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3131. Min Act: -0.0000

Data Index: 879126 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1098660 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2634. Min Act: -0.0000

Data Index: 149863 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1867087 (The Pile)

Max Activating Token Index: 886