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

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

Neuron 4421 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.7574. Min Act: -0.0000

Data Index: 1487270 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.4630. Min Act: -0.0000

Data Index: 1599643 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.3884. Min Act: -0.0000

Data Index: 1429273 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.0607. Min Act: -0.0000

Data Index: 1412133 (Python Code)

Max Activating Token Index: 850

Text #4

Max Range: 6.7574. Min Range: -6.7574

Max Act: 5.8929. Min Act: -0.0000

Data Index: 1541995 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.1994. Min Act: -0.0000

Data Index: 1372160 (Python Code)

Max Activating Token Index: 556

Text #6

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.1728. Min Act: -0.0000

Data Index: 1505239 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.1639. Min Act: -0.0000

Data Index: 1652529 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 6.7574. Min Range: -6.7574

Max Act: 5.9679. Min Act: -0.0000

Data Index: 1640848 (Python Code)

Max Activating Token Index: 226

Text #9

Max Range: 6.7574. Min Range: -6.7574

Max Act: 5.9498. Min Act: -0.0000

Data Index: 1433437 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.0881. Min Act: -0.0000

Data Index: 1550221 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.2753. Min Act: -0.0000

Data Index: 1451794 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.1094. Min Act: -0.0000

Data Index: 1423163 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.0955. Min Act: -0.0000

Data Index: 1656789 (Python Code)

Max Activating Token Index: 502

Text #14

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.0921. Min Act: -0.0000

Data Index: 1515195 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.2201. Min Act: -0.0000

Data Index: 1365016 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.0731. Min Act: -0.0000

Data Index: 1383515 (Python Code)

Max Activating Token Index: 554

Text #17

Max Range: 6.7574. Min Range: -6.7574

Max Act: 5.8508. Min Act: -0.0000

Data Index: 1404359 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.0384. Min Act: -0.0000

Data Index: 1419258 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 6.7574. Min Range: -6.7574

Max Act: 6.2378. Min Act: -0.0000

Data Index: 1616306 (Python Code)

Max Activating Token Index: 724