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

Dataset: The Pile

Neuron 260 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1022936 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1360673 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1319337 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1227401 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1869765 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5988. Min Act: -0.0000

Data Index: 796609 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5921. Min Act: 0.0000

Data Index: 1452479 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1907253 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5781. Min Act: 0.0000

Data Index: 682326 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6029. Min Act: -0.0000

Data Index: 662616 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1178964 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5934. Min Act: 0.0000

Data Index: 743047 (The Pile)

Max Activating Token Index: 328

Text #12

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6435. Min Act: -0.0000

Data Index: 92975 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1257370 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5785. Min Act: -0.0000

Data Index: 156153 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1281253 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1733762 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5709. Min Act: 0.0000

Data Index: 1936269 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5834. Min Act: 0.0000

Data Index: 860511 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5479. Min Act: -0.0000

Data Index: 36789 (The Pile)

Max Activating Token Index: 461