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

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

Neuron 3609 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3388. Min Range: -5.3388

Max Act: 5.3388. Min Act: -0.0000

Data Index: 1516391 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 5.3388. Min Range: -5.3388

Max Act: 5.2059. Min Act: -0.0000

Data Index: 1453735 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 5.3388. Min Range: -5.3388

Max Act: 5.1246. Min Act: -0.0000

Data Index: 1402110 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.6840. Min Act: -0.0000

Data Index: 1463678 (Python Code)

Max Activating Token Index: 667

Text #4

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.6315. Min Act: -0.0000

Data Index: 1534849 (Python Code)

Max Activating Token Index: 986

Text #5

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.6050. Min Act: -0.0000

Data Index: 1557121 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.3889. Min Act: -0.0000

Data Index: 1627193 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.1774. Min Act: -0.0000

Data Index: 1640366 (Python Code)

Max Activating Token Index: 629

Text #8

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.3712. Min Act: -0.0000

Data Index: 1636637 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.2941. Min Act: -0.0000

Data Index: 1558326 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 5.3388. Min Range: -5.3388

Max Act: 3.9767. Min Act: -0.0000

Data Index: 1606852 (Python Code)

Max Activating Token Index: 352

Text #11

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.2524. Min Act: -0.0000

Data Index: 1533400 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.1148. Min Act: -0.0000

Data Index: 1465286 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 5.3388. Min Range: -5.3388

Max Act: 3.7795. Min Act: -0.0000

Data Index: 1362342 (Python Code)

Max Activating Token Index: 976

Text #14

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.0754. Min Act: -0.0000

Data Index: 1391161 (Python Code)

Max Activating Token Index: 781

Text #15

Max Range: 5.3388. Min Range: -5.3388

Max Act: 3.8951. Min Act: -0.0000

Data Index: 1517659 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.2155. Min Act: -0.0000

Data Index: 1392971 (Python Code)

Max Activating Token Index: 690

Text #17

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.0242. Min Act: -0.0000

Data Index: 1604907 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 5.3388. Min Range: -5.3388

Max Act: 3.9790. Min Act: -0.0000

Data Index: 1436174 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 5.3388. Min Range: -5.3388

Max Act: 4.1203. Min Act: -0.0000

Data Index: 1583159 (Python Code)

Max Activating Token Index: 1023