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

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

Neuron 3580 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: 4.9630. Min Range: -4.9630

Max Act: 4.9630. Min Act: -0.0000

Data Index: 1365518 (Python Code)

Max Activating Token Index: 361

Text #1

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.9418. Min Act: -0.0000

Data Index: 1482329 (Python Code)

Max Activating Token Index: 429

Text #2

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.7758. Min Act: -0.0000

Data Index: 1600444 (Python Code)

Max Activating Token Index: 300

Text #3

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.7836. Min Act: -0.0000

Data Index: 1473660 (Python Code)

Max Activating Token Index: 538

Text #4

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.7631. Min Act: -0.0000

Data Index: 1476922 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.9622. Min Act: -0.0000

Data Index: 1553764 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.7449. Min Act: -0.0000

Data Index: 1586664 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.9102. Min Act: -0.0000

Data Index: 1544968 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.7717. Min Act: -0.0000

Data Index: 1597387 (Python Code)

Max Activating Token Index: 921

Text #9

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.6040. Min Act: -0.0000

Data Index: 629878 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.5711. Min Act: -0.0000

Data Index: 1511865 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.3959. Min Act: -0.0000

Data Index: 1611765 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.5578. Min Act: -0.0000

Data Index: 1421010 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.5030. Min Act: -0.0000

Data Index: 1562364 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.4180. Min Act: -0.0000

Data Index: 927283 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.4038. Min Act: -0.0000

Data Index: 1570209 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.5465. Min Act: -0.0000

Data Index: 1404558 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.5706. Min Act: -0.0000

Data Index: 1592963 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.5517. Min Act: -0.0000

Data Index: 1409178 (Python Code)

Max Activating Token Index: 228

Text #19

Max Range: 4.9630. Min Range: -4.9630

Max Act: 4.5502. Min Act: -0.0000

Data Index: 1322004 (C4 (Web Text))

Max Activating Token Index: 503