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

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

Neuron 1012 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: 0.9268. Min Range: -0.9268

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1510214 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1451244 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1528306 (Python Code)

Max Activating Token Index: 209

Text #3

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1484929 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1446881 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1425059 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1461324 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1518504 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1449235 (Python Code)

Max Activating Token Index: 179

Text #9

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1475865 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1434588 (Python Code)

Max Activating Token Index: 628

Text #11

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1544808 (Python Code)

Max Activating Token Index: 663

Text #12

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1398873 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1649029 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1529201 (Python Code)

Max Activating Token Index: 887

Text #15

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1531014 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1389372 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1558982 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1531649 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1385503 (Python Code)

Max Activating Token Index: 898