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

Dataset: The Pile

Neuron 3841 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: 1.7126. Min Range: -1.7126

Max Act: 1.6005. Min Act: -0.0000

Data Index: 1713854 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.7126. Min Act: -0.0000

Data Index: 1153848 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6103. Min Act: -0.0000

Data Index: 1013529 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.5765. Min Act: -0.0000

Data Index: 951340 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1871516 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1049653 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.3291. Min Act: -0.0000

Data Index: 842709 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.3739. Min Act: -0.0000

Data Index: 392858 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.4812. Min Act: -0.0000

Data Index: 666106 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1833878 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1454831 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.4516. Min Act: -0.0000

Data Index: 452275 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1827328 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.3362. Min Act: -0.0000

Data Index: 400124 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1067283 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.4915. Min Act: -0.0000

Data Index: 608509 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.3542. Min Act: -0.0000

Data Index: 1161766 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1558310 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1101938 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1583728 (The Pile)

Max Activating Token Index: 322