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

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

Neuron 2690 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1599056 (Python Code)

Max Activating Token Index: 917

Text #1

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1078907 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1133883 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1787. Min Act: -0.0000

Data Index: 846306 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1311. Min Act: -0.0000

Data Index: 310914 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1175195 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1441. Min Act: -0.0000

Data Index: 301694 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1233614 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1492. Min Act: -0.0000

Data Index: 15467 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1414. Min Act: -0.0000

Data Index: 643705 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1118346 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1245. Min Act: -0.0000

Data Index: 185720 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1536. Min Act: -0.0000

Data Index: 537268 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1430. Min Act: -0.0000

Data Index: 561842 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1475. Min Act: -0.0000

Data Index: 53671 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1045092 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1251436 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1223. Min Act: -0.0000

Data Index: 359474 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1340. Min Act: -0.0000

Data Index: 682916 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1398. Min Act: -0.0000

Data Index: 790344 (C4 (Web Text))

Max Activating Token Index: 349