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

Dataset: The Pile

Neuron 2157 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1194167 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: 0.0000

Data Index: 1840588 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1102. Min Act: 0.0000

Data Index: 1427078 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1093. Min Act: 0.0000

Data Index: 812448 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1070. Min Act: -0.0000

Data Index: 897171 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1727047 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1675221 (The Pile)

Max Activating Token Index: 595

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1039. Min Act: 0.0000

Data Index: 514349 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1040. Min Act: 0.0000

Data Index: 723313 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1020. Min Act: 0.0000

Data Index: 1813138 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1011. Min Act: 0.0000

Data Index: 441629 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1012. Min Act: 0.0000

Data Index: 758557 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1001. Min Act: 0.0000

Data Index: 199461 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1003. Min Act: -0.0000

Data Index: 694292 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1872929 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0981. Min Act: 0.0000

Data Index: 92938 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0975. Min Act: 0.0000

Data Index: 787617 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0975. Min Act: 0.0000

Data Index: 1662194 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1417576 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0971. Min Act: 0.0000

Data Index: 1545310 (The Pile)

Max Activating Token Index: 912