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

Dataset: The Pile

Neuron 2631 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: 0.1013. Min Range: -0.1013

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1212713 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1993662 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1411219 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0951. Min Act: -0.0000

Data Index: 543299 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1009. Min Act: -0.0000

Data Index: 600306 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1161908 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1073400 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0880. Min Act: -0.0000

Data Index: 546200 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0874. Min Act: -0.0000

Data Index: 868076 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1923752 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1827934 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0867. Min Act: -0.0000

Data Index: 312284 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0910. Min Act: -0.0000

Data Index: 398897 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1976489 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0000

Data Index: 901264 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0926. Min Act: -0.0000

Data Index: 835852 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0900. Min Act: -0.0000

Data Index: 611013 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1240016 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1551810 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0828. Min Act: -0.0000

Data Index: 316699 (The Pile)

Max Activating Token Index: 197