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

Dataset: The Pile

Neuron 859 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: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: 0.0000

Data Index: 1053750 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1182. Min Act: 0.0000

Data Index: 430591 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1192. Min Act: 0.0000

Data Index: 1074068 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1190. Min Act: 0.0000

Data Index: 358547 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1122. Min Act: 0.0000

Data Index: 218100 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1099. Min Act: 0.0000

Data Index: 393101 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1132. Min Act: 0.0000

Data Index: 325193 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1111. Min Act: 0.0000

Data Index: 1679275 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1092. Min Act: 0.0000

Data Index: 798817 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1125. Min Act: 0.0000

Data Index: 985795 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1080. Min Act: 0.0000

Data Index: 1196701 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1070. Min Act: 0.0000

Data Index: 708789 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1065. Min Act: 0.0000

Data Index: 1884571 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1046. Min Act: 0.0000

Data Index: 830790 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1041. Min Act: -0.0000

Data Index: 731506 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1035. Min Act: 0.0000

Data Index: 1666032 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1025. Min Act: -0.0000

Data Index: 998483 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1024. Min Act: 0.0000

Data Index: 921703 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1022. Min Act: 0.0000

Data Index: 982774 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1021. Min Act: 0.0000

Data Index: 1352315 (The Pile)

Max Activating Token Index: 1023