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

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

Neuron 943 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: 0.7694. Min Range: -0.7694

Max Act: 0.7694. Min Act: -0.0001

Data Index: 1604546 (Python Code)

Max Activating Token Index: 975

Text #1

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1640678 (Python Code)

Max Activating Token Index: 627

Text #2

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1409026 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1584339 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1402810 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1644400 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1495874 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1574711 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1572936 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1535408 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1639206 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1603882 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1391503 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1555554 (Python Code)

Max Activating Token Index: 435

Text #14

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1655522 (Python Code)

Max Activating Token Index: 444

Text #15

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1424865 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1450191 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1378749 (Python Code)

Max Activating Token Index: 613

Text #18

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1584204 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1428566 (Python Code)

Max Activating Token Index: 78