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

Dataset: The Pile

Neuron 4396 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: 1.5892. Min Range: -1.5892

Max Act: 1.5892. Min Act: -0.0000

Data Index: 772543 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.5440. Min Act: -0.0000

Data Index: 1993943 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.4350. Min Act: -0.0000

Data Index: 77758 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.4873. Min Act: -0.0000

Data Index: 917344 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.4718. Min Act: -0.0000

Data Index: 1726244 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3726. Min Act: -0.0000

Data Index: 832286 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1080473 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1406767 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.4319. Min Act: -0.0000

Data Index: 308121 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1856587 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1368649 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2040. Min Act: -0.0000

Data Index: 198437 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2135. Min Act: -0.0000

Data Index: 772816 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2082. Min Act: -0.0000

Data Index: 82420 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1200973 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2759. Min Act: -0.0000

Data Index: 1955159 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1091821 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2529. Min Act: -0.0000

Data Index: 466139 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2651. Min Act: -0.0000

Data Index: 572033 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2682. Min Act: -0.0000

Data Index: 497386 (The Pile)

Max Activating Token Index: 912