Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1728 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1387. Min Act: -0.0002

Data Index: 506586 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1270. Min Act: -0.0002

Data Index: 459506 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1266. Min Act: -0.0002

Data Index: 521567 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1361. Min Act: -0.0002

Data Index: 770971 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1109. Min Act: -0.0002

Data Index: 238417 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1212. Min Act: -0.0002

Data Index: 680929 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1221. Min Act: -0.0002

Data Index: 412081 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1239. Min Act: -0.0002

Data Index: 809512 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1258039 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1064. Min Act: -0.0002

Data Index: 250044 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1131. Min Act: -0.0002

Data Index: 955376 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1029. Min Act: -0.0002

Data Index: 987830 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1018. Min Act: -0.0002

Data Index: 727897 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1008. Min Act: -0.0002

Data Index: 453212 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1017. Min Act: -0.0002

Data Index: 682410 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1159532 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0932. Min Act: -0.0002

Data Index: 153752 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0997. Min Act: -0.0002

Data Index: 63005 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0985. Min Act: -0.0002

Data Index: 568205 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1135138 (C4 (Web Text))

Max Activating Token Index: 774