Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3222 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1259013 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1252. Min Act: -0.0001

Data Index: 45941 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0001

Data Index: 832892 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1085. Min Act: -0.0001

Data Index: 107279 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1020. Min Act: -0.0001

Data Index: 314442 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1166016 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1069221 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1106. Min Act: -0.0001

Data Index: 766370 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0980. Min Act: -0.0001

Data Index: 913029 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1046523 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0977. Min Act: -0.0001

Data Index: 708778 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1103. Min Act: -0.0001

Data Index: 695785 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1333395 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1352793 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0889. Min Act: -0.0001

Data Index: 465951 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1018. Min Act: -0.0001

Data Index: 431590 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1019. Min Act: -0.0001

Data Index: 932539 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1014. Min Act: -0.0001

Data Index: 644059 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1319771 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1260801 (C4 (Web Text))

Max Activating Token Index: 890