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

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

Neuron 2067 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6387. Min Range: -2.6387

Max Act: 2.6387. Min Act: -0.0000

Data Index: 143458 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 2.6387. Min Range: -2.6387

Max Act: 2.5505. Min Act: -0.0000

Data Index: 1284269 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 2.6387. Min Range: -2.6387

Max Act: 2.0891. Min Act: -0.0000

Data Index: 492776 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.4976. Min Act: 0.0000

Data Index: 271506 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.6177. Min Act: -0.0000

Data Index: 734834 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.4313. Min Act: 0.0000

Data Index: 223181 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.5499. Min Act: -0.0000

Data Index: 1167532 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.4480. Min Act: -0.0000

Data Index: 888492 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.1416. Min Act: -0.0000

Data Index: 630758 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.2822. Min Act: -0.0000

Data Index: 777616 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.3484. Min Act: -0.0000

Data Index: 939291 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.2761. Min Act: -0.0000

Data Index: 28769 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.2415. Min Act: -0.0000

Data Index: 894561 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.0580. Min Act: 0.0000

Data Index: 728814 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.2004. Min Act: -0.0000

Data Index: 165197 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.1980. Min Act: -0.0000

Data Index: 202184 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.1426. Min Act: 0.0000

Data Index: 318155 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1281827 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.1675. Min Act: -0.0000

Data Index: 495094 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 2.6387. Min Range: -2.6387

Max Act: 1.1156. Min Act: -0.0000

Data Index: 605422 (C4 (Web Text))

Max Activating Token Index: 684