Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1969 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1446039 (Python Code)

Max Activating Token Index: 315

Text #1

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1407478 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1422221 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1445845 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1640781 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9794. Min Act: -0.0000

Data Index: 846107 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1632408 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1421434 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1514597 (Python Code)

Max Activating Token Index: 420

Text #9

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1483773 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1411533 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1588755 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1477703 (Python Code)

Max Activating Token Index: 856

Text #13

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0813. Min Act: -0.0000

Data Index: 1611652 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1488184 (Python Code)

Max Activating Token Index: 337

Text #15

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1539005 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1537208 (Python Code)

Max Activating Token Index: 756

Text #17

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1438815 (Python Code)

Max Activating Token Index: 842

Text #18

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1537019 (Python Code)

Max Activating Token Index: 556

Text #19

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1552142 (Python Code)

Max Activating Token Index: 111