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

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

Neuron 3713 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1697. Min Act: -0.0000

Data Index: 190765 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1580. Min Act: -0.0000

Data Index: 879440 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1558. Min Act: -0.0000

Data Index: 672397 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1234792 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1510. Min Act: -0.0000

Data Index: 765525 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1531. Min Act: -0.0000

Data Index: 1202737 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1666. Min Act: -0.0000

Data Index: 90800 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1260354 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1442. Min Act: -0.0000

Data Index: 210329 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1531. Min Act: -0.0000

Data Index: 1298951 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1351. Min Act: -0.0000

Data Index: 462260 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1385. Min Act: -0.0000

Data Index: 2882 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1100307 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1196658 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1402. Min Act: -0.0000

Data Index: 960025 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1456. Min Act: -0.0000

Data Index: 460492 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1252. Min Act: -0.0000

Data Index: 997077 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1285884 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1336. Min Act: -0.0000

Data Index: 888520 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1378. Min Act: -0.0000

Data Index: 571677 (C4 (Web Text))

Max Activating Token Index: 272