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

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

Neuron 1364 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: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0000

Data Index: 251942 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1651. Min Act: -0.0000

Data Index: 661596 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1678. Min Act: -0.0000

Data Index: 480729 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1710. Min Act: -0.0000

Data Index: 102138 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1541. Min Act: -0.0000

Data Index: 153770 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1705. Min Act: -0.0000

Data Index: 170430 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1681. Min Act: -0.0000

Data Index: 893140 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1015733 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1626. Min Act: -0.0000

Data Index: 692529 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1560. Min Act: -0.0000

Data Index: 556878 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1002242 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1273692 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1288866 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1429. Min Act: -0.0000

Data Index: 851897 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1443. Min Act: -0.0000

Data Index: 302199 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1324. Min Act: -0.0000

Data Index: 623436 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1093689 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1012576 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1115439 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1309. Min Act: -0.0000

Data Index: 366549 (C4 (Web Text))

Max Activating Token Index: 1018