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

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

Neuron 3448 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1878. Min Act: -0.0000

Data Index: 451846 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1719. Min Act: -0.0000

Data Index: 890199 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1827. Min Act: -0.0000

Data Index: 198952 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1541. Min Act: -0.0000

Data Index: 294995 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1597. Min Act: -0.0000

Data Index: 259584 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1542. Min Act: -0.0000

Data Index: 366738 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1612. Min Act: -0.0000

Data Index: 128327 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1434. Min Act: -0.0000

Data Index: 31874 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1025229 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1432. Min Act: -0.0000

Data Index: 111146 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1396. Min Act: -0.0000

Data Index: 787219 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1381. Min Act: -0.0001

Data Index: 976749 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1462. Min Act: -0.0000

Data Index: 527140 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1442. Min Act: -0.0000

Data Index: 45639 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1440. Min Act: -0.0000

Data Index: 546800 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1469. Min Act: -0.0000

Data Index: 5044 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1335. Min Act: -0.0000

Data Index: 220080 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1320. Min Act: -0.0000

Data Index: 815910 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1362. Min Act: -0.0000

Data Index: 825619 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1369. Min Act: -0.0000

Data Index: 347484 (C4 (Web Text))

Max Activating Token Index: 534