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

Dataset: The Pile

Neuron 4969 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0000

Data Index: 228285 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1814434 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1114. Min Act: -0.0000

Data Index: 271580 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1037812 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1112. Min Act: -0.0000

Data Index: 285195 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1048. Min Act: -0.0000

Data Index: 657119 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1639772 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1604860 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1038. Min Act: -0.0000

Data Index: 249240 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1318452 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1232201 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1152521 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0984. Min Act: -0.0000

Data Index: 343027 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1050. Min Act: -0.0000

Data Index: 190124 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1567564 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1051. Min Act: -0.0000

Data Index: 601416 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1004. Min Act: -0.0000

Data Index: 166415 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1039. Min Act: -0.0000

Data Index: 505255 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1264350 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1087. Min Act: -0.0000

Data Index: 22230 (The Pile)

Max Activating Token Index: 581