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

Dataset: The Pile

Neuron 2224 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: 0.1112. Min Range: -0.1112

Max Act: 0.1112. Min Act: 0.0000

Data Index: 1503188 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1093. Min Act: 0.0000

Data Index: 1292949 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1286603 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1079. Min Act: 0.0000

Data Index: 1528438 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1073. Min Act: -0.0000

Data Index: 122792 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1065. Min Act: 0.0000

Data Index: 1323070 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1060. Min Act: 0.0000

Data Index: 1703150 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1052. Min Act: 0.0000

Data Index: 1315277 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1047. Min Act: 0.0000

Data Index: 938147 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1036. Min Act: 0.0000

Data Index: 71944 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1021. Min Act: 0.0000

Data Index: 816822 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1010. Min Act: 0.0000

Data Index: 1384878 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1010. Min Act: 0.0000

Data Index: 1004513 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1534650 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0998. Min Act: 0.0000

Data Index: 1204100 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0995. Min Act: 0.0000

Data Index: 937445 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0986. Min Act: 0.0000

Data Index: 1101922 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0985. Min Act: -0.0000

Data Index: 122795 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0968. Min Act: 0.0000

Data Index: 894130 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0955. Min Act: 0.0000

Data Index: 615517 (The Pile)

Max Activating Token Index: 1023