Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 652 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1848645 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1021. Min Act: -0.0001

Data Index: 183479 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1150093 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1040213 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0972. Min Act: -0.0001

Data Index: 932273 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1669834 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0937. Min Act: -0.0001

Data Index: 864768 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1045. Min Act: -0.0001

Data Index: 832687 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1522307 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1863782 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0834. Min Act: -0.0001

Data Index: 155233 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1392001 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1990777 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0843. Min Act: -0.0001

Data Index: 268851 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0837. Min Act: -0.0001

Data Index: 140470 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0855. Min Act: -0.0001

Data Index: 329832 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0970. Min Act: -0.0001

Data Index: 355009 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0848. Min Act: -0.0001

Data Index: 731267 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0774. Min Act: -0.0001

Data Index: 486722 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1393182 (The Pile)

Max Activating Token Index: 942