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

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

Neuron 3823 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1387. Min Act: -0.0000

Data Index: 904851 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1335. Min Act: -0.0000

Data Index: 231815 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1285. Min Act: -0.0000

Data Index: 548879 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1316. Min Act: -0.0000

Data Index: 81461 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1306. Min Act: -0.0000

Data Index: 935767 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1290. Min Act: -0.0000

Data Index: 343174 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1273455 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1201. Min Act: -0.0000

Data Index: 684827 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1125. Min Act: -0.0000

Data Index: 819552 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1147. Min Act: -0.0000

Data Index: 655905 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1141. Min Act: -0.0000

Data Index: 79245 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1087. Min Act: -0.0000

Data Index: 586282 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1040. Min Act: -0.0000

Data Index: 447907 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1071. Min Act: -0.0000

Data Index: 846663 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1072. Min Act: -0.0000

Data Index: 172120 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1298456 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1054. Min Act: -0.0000

Data Index: 283349 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1066. Min Act: -0.0000

Data Index: 151853 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1073. Min Act: -0.0000

Data Index: 293472 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1085. Min Act: -0.0000

Data Index: 664906 (C4 (Web Text))

Max Activating Token Index: 549