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

Dataset: The Pile

Neuron 751 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: 0.0032. Min Range: -0.0032

Max Act: 0.0032. Min Act: -0.0000

Data Index: 1077791 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0030. Min Act: -0.0000

Data Index: 143685 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0029. Min Act: -0.0000

Data Index: 186490 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0029. Min Act: -0.0000

Data Index: 245171 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0029. Min Act: -0.0000

Data Index: 1746182 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0000

Data Index: 205539 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0000

Data Index: 456534 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0000

Data Index: 1093275 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0000

Data Index: 1982161 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0000

Data Index: 987481 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0000

Data Index: 455679 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1494993 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 277783 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 429044 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1754751 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1306033 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1779694 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1745960 (The Pile)

Max Activating Token Index: 87

Text #18

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1202992 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0026. Min Act: -0.0000

Data Index: 120210 (The Pile)

Max Activating Token Index: 23