Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2762 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1896. Min Act: -0.0000

Data Index: 169249 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1698. Min Act: -0.0000

Data Index: 797104 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1689. Min Act: -0.0000

Data Index: 718342 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1473377 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1483421 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1519406 (Python Code)

Max Activating Token Index: 938

Text #6

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1524. Min Act: -0.0000

Data Index: 312731 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1245390 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1514914 (Python Code)

Max Activating Token Index: 614

Text #9

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1596424 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1589. Min Act: -0.0000

Data Index: 414331 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1537621 (Python Code)

Max Activating Token Index: 837

Text #12

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1379126 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1231453 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1507275 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1355. Min Act: -0.0000

Data Index: 854738 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1528291 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1125583 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1445. Min Act: -0.0001

Data Index: 848155 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1350. Min Act: -0.0000

Data Index: 863795 (C4 (Web Text))

Max Activating Token Index: 444