Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5363 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2387. Min Act: -0.0000

Data Index: 179190 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1002520 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1630. Min Act: -0.0000

Data Index: 484726 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1624. Min Act: -0.0000

Data Index: 232755 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1623. Min Act: -0.0000

Data Index: 20523 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1583. Min Act: -0.0000

Data Index: 169447 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1079749 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1563. Min Act: -0.0000

Data Index: 117977 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1476. Min Act: -0.0000

Data Index: 939889 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1282380 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1328612 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1439. Min Act: -0.0000

Data Index: 484367 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1428. Min Act: -0.0000

Data Index: 183070 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1427. Min Act: -0.0000

Data Index: 744822 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1423. Min Act: -0.0000

Data Index: 320611 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1389. Min Act: -0.0000

Data Index: 24074 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1429. Min Act: -0.0000

Data Index: 662790 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1021133 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1352. Min Act: -0.0000

Data Index: 687061 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1381. Min Act: -0.0000

Data Index: 656340 (C4 (Web Text))

Max Activating Token Index: 247