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

Dataset: The Pile

Neuron 4540 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: 0.1171. Min Range: -0.1171

Max Act: 0.1171. Min Act: 0.0000

Data Index: 1648112 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1113. Min Act: 0.0000

Data Index: 1798656 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1098. Min Act: -0.0000

Data Index: 911262 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1091. Min Act: 0.0000

Data Index: 1496208 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1435202 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1077. Min Act: 0.0000

Data Index: 401073 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1061. Min Act: -0.0000

Data Index: 981480 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1045. Min Act: 0.0000

Data Index: 1980136 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1182184 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1038. Min Act: 0.0000

Data Index: 1732442 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1876605 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1075. Min Act: 0.0000

Data Index: 332992 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1018. Min Act: 0.0000

Data Index: 1714612 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1016. Min Act: 0.0000

Data Index: 983451 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1053. Min Act: 0.0000

Data Index: 669400 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1014. Min Act: 0.0000

Data Index: 429684 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1058678 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1005. Min Act: 0.0000

Data Index: 1636772 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1001. Min Act: 0.0000

Data Index: 1667932 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1001. Min Act: -0.0000

Data Index: 787070 (The Pile)

Max Activating Token Index: 1023