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

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

Neuron 626 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2357. Min Act: -0.0000

Data Index: 480448 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2387. Min Act: -0.0001

Data Index: 790718 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2301. Min Act: -0.0000

Data Index: 923789 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1000806 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2236. Min Act: -0.0001

Data Index: 727592 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2095. Min Act: -0.0001

Data Index: 192254 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2119. Min Act: -0.0001

Data Index: 880454 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2248. Min Act: -0.0000

Data Index: 231387 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1217715 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1206097 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1318661 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2080. Min Act: -0.0001

Data Index: 694611 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1901. Min Act: -0.0001

Data Index: 551047 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1752. Min Act: -0.0001

Data Index: 381502 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1719. Min Act: -0.0001

Data Index: 607351 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1103985 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1742. Min Act: -0.0001

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1522. Min Act: -0.0001

Data Index: 327734 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1003093 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1163267 (C4 (Web Text))

Max Activating Token Index: 644