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

Dataset: The Pile

Neuron 2161 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.9133. Min Act: -0.0000

Data Index: 536394 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.8841. Min Act: -0.0000

Data Index: 1548256 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.9251. Min Act: -0.0000

Data Index: 1326322 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.6199. Min Act: -0.0000

Data Index: 859620 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5912. Min Act: -0.0000

Data Index: 1225525 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.6952. Min Act: -0.0000

Data Index: 378307 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5331. Min Act: -0.0000

Data Index: 801241 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1633797 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4086. Min Act: -0.0000

Data Index: 618716 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1085917 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4184. Min Act: -0.0000

Data Index: 184858 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1949990 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.2818. Min Act: -0.0000

Data Index: 146635 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.3542. Min Act: -0.0000

Data Index: 1511556 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4003. Min Act: -0.0000

Data Index: 921934 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.3908. Min Act: -0.0000

Data Index: 1995642 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.3568. Min Act: -0.0000

Data Index: 692379 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.3024. Min Act: -0.0000

Data Index: 781021 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.2981. Min Act: -0.0000

Data Index: 424837 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4063. Min Act: -0.0000

Data Index: 1008566 (The Pile)

Max Activating Token Index: 141