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

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

Neuron 3632 in Layer 7

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: 0.2349. Min Act: -0.0000

Data Index: 893076 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2387. Min Act: -0.0000

Data Index: 699234 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1355883 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2187. Min Act: -0.0001

Data Index: 457528 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2153. Min Act: -0.0001

Data Index: 228535 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2131. Min Act: -0.0000

Data Index: 130252 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2127. Min Act: -0.0000

Data Index: 806012 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2106. Min Act: -0.0001

Data Index: 658600 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2152. Min Act: -0.0000

Data Index: 31688 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1928. Min Act: -0.0001

Data Index: 907733 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1980. Min Act: -0.0000

Data Index: 28417 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2020. Min Act: -0.0001

Data Index: 993541 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1893. Min Act: -0.0000

Data Index: 33916 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1341486 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2096. Min Act: -0.0000

Data Index: 844041 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1929. Min Act: -0.0000

Data Index: 432279 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1915. Min Act: -0.0000

Data Index: 245729 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1917. Min Act: -0.0000

Data Index: 374530 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1786. Min Act: -0.0000

Data Index: 406182 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1781. Min Act: -0.0000

Data Index: 904250 (C4 (Web Text))

Max Activating Token Index: 238