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

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

Neuron 2096 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.2872. Min Act: -0.0002

Data Index: 1042015 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.2676. Min Act: -0.0003

Data Index: 1445360 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.2024. Min Act: -0.0002

Data Index: 1395482 (Python Code)

Max Activating Token Index: 375

Text #3

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.1669. Min Act: -0.0002

Data Index: 130035 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0888. Min Act: -0.0002

Data Index: 1602609 (Python Code)

Max Activating Token Index: 912

Text #5

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.1374. Min Act: -0.0002

Data Index: 1526097 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.1433. Min Act: -0.0003

Data Index: 1561321 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0459. Min Act: -0.0002

Data Index: 1450536 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0579. Min Act: -0.0002

Data Index: 1393182 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0429. Min Act: -0.0002

Data Index: 695381 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0301. Min Act: -0.0002

Data Index: 1540015 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0543. Min Act: -0.0003

Data Index: 1572426 (Python Code)

Max Activating Token Index: 481

Text #12

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0423. Min Act: -0.0003

Data Index: 1595385 (Python Code)

Max Activating Token Index: 470

Text #13

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0269. Min Act: -0.0002

Data Index: 1403246 (Python Code)

Max Activating Token Index: 722

Text #14

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0158. Min Act: -0.0002

Data Index: 1605010 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0103. Min Act: -0.0002

Data Index: 1507226 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0047. Min Act: -0.0002

Data Index: 1042042 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0016. Min Act: -0.0002

Data Index: 1378756 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.9973. Min Act: -0.0002

Data Index: 1530497 (Python Code)

Max Activating Token Index: 411

Text #19

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.9767. Min Act: -0.0003

Data Index: 153073 (C4 (Web Text))

Max Activating Token Index: 539