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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4626 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1138. Min Act: -0.0001

Data Index: 832356 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1022863 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1074. Min Act: -0.0001

Data Index: 752940 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1102. Min Act: -0.0001

Data Index: 985291 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1135. Min Act: -0.0001

Data Index: 944450 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1241521 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1308817 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1047. Min Act: -0.0001

Data Index: 227739 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1081. Min Act: -0.0001

Data Index: 327232 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1156855 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1051. Min Act: -0.0001

Data Index: 487772 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1073611 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1039. Min Act: -0.0001

Data Index: 903983 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1018. Min Act: -0.0001

Data Index: 632792 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1088. Min Act: -0.0001

Data Index: 724662 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1283695 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1008714 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0991. Min Act: -0.0001

Data Index: 997392 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0856. Min Act: -0.0001

Data Index: 198096 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0939. Min Act: -0.0001

Data Index: 932262 (C4 (Web Text))

Max Activating Token Index: 674