Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 339 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0003

Data Index: 224494 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0375. Min Act: -0.0003

Data Index: 609265 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0379. Min Act: -0.0003

Data Index: 77598 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1068240 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0376. Min Act: -0.0003

Data Index: 193817 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0354. Min Act: -0.0004

Data Index: 655358 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1000655 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0357. Min Act: -0.0003

Data Index: 212855 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0361. Min Act: -0.0004

Data Index: 1206170 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1202661 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0366. Min Act: -0.0004

Data Index: 18930 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0340. Min Act: -0.0003

Data Index: 90009 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0349. Min Act: -0.0003

Data Index: 880423 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0349. Min Act: -0.0003

Data Index: 449007 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0353. Min Act: -0.0003

Data Index: 432877 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0341. Min Act: -0.0003

Data Index: 79936 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0345. Min Act: -0.0003

Data Index: 584477 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1206867 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0346. Min Act: -0.0003

Data Index: 980409 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0342. Min Act: -0.0003

Data Index: 356023 (C4 (Web Text))

Max Activating Token Index: 164