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

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

Neuron 558 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1850. Min Act: -0.0000

Data Index: 464580 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1616. Min Act: -0.0000

Data Index: 59513 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1045727 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1464. Min Act: -0.0000

Data Index: 727605 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1011464 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1476. Min Act: -0.0000

Data Index: 967403 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1467. Min Act: -0.0000

Data Index: 828432 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1033950 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1441. Min Act: -0.0000

Data Index: 229081 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1412. Min Act: -0.0000

Data Index: 191318 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1467. Min Act: -0.0000

Data Index: 825987 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1215765 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1397. Min Act: -0.0000

Data Index: 964267 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1389. Min Act: -0.0000

Data Index: 72442 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1284. Min Act: -0.0000

Data Index: 660117 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1165133 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1358. Min Act: -0.0000

Data Index: 370305 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1354. Min Act: -0.0000

Data Index: 496423 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1364. Min Act: -0.0000

Data Index: 349388 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1352. Min Act: -0.0000

Data Index: 88272 (C4 (Web Text))

Max Activating Token Index: 477