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

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

Neuron 2413 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8302. Min Range: -4.8302

Max Act: 4.8302. Min Act: -0.0000

Data Index: 1460995 (Python Code)

Max Activating Token Index: 523

Text #1

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.8331. Min Act: -0.0000

Data Index: 1461979 (Python Code)

Max Activating Token Index: 694

Text #2

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.7550. Min Act: -0.0000

Data Index: 1476635 (Python Code)

Max Activating Token Index: 788

Text #3

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.9760. Min Act: -0.0000

Data Index: 1615493 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 4.8302. Min Range: -4.8302

Max Act: 4.2320. Min Act: -0.0000

Data Index: 1399423 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 4.8302. Min Range: -4.8302

Max Act: 4.2189. Min Act: -0.0000

Data Index: 1387191 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 4.8302. Min Range: -4.8302

Max Act: 4.1501. Min Act: -0.0000

Data Index: 1485907 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.9522. Min Act: -0.0000

Data Index: 1360495 (Python Code)

Max Activating Token Index: 822

Text #8

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.9550. Min Act: -0.0000

Data Index: 1561776 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 4.8302. Min Range: -4.8302

Max Act: 4.0609. Min Act: -0.0000

Data Index: 1461719 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.8619. Min Act: -0.0000

Data Index: 1423618 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.7014. Min Act: -0.0000

Data Index: 1564424 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.7763. Min Act: -0.0000

Data Index: 1495392 (Python Code)

Max Activating Token Index: 723

Text #13

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.9429. Min Act: -0.0000

Data Index: 1378711 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.5970. Min Act: -0.0000

Data Index: 1611232 (Python Code)

Max Activating Token Index: 137

Text #15

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.7649. Min Act: -0.0000

Data Index: 1613163 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.5700. Min Act: -0.0000

Data Index: 1435062 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.7311. Min Act: -0.0000

Data Index: 1374728 (Python Code)

Max Activating Token Index: 973

Text #18

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.8758. Min Act: -0.0000

Data Index: 1407478 (Python Code)

Max Activating Token Index: 642

Text #19

Max Range: 4.8302. Min Range: -4.8302

Max Act: 3.6187. Min Act: -0.0000

Data Index: 1598219 (Python Code)

Max Activating Token Index: 552