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

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

Neuron 4857 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1426822 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1517945 (Python Code)

Max Activating Token Index: 467

Text #2

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1584314 (Python Code)

Max Activating Token Index: 157

Text #3

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1606044 (Python Code)

Max Activating Token Index: 441

Text #4

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1498213 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1416541 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1634808 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1597963 (Python Code)

Max Activating Token Index: 367

Text #8

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1387708 (Python Code)

Max Activating Token Index: 733

Text #9

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1654389 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1624295 (Python Code)

Max Activating Token Index: 279

Text #11

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1577156 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1413181 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5606. Min Act: -0.0000

Data Index: 825463 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5499. Min Act: -0.0000

Data Index: 102482 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1589276 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1415969 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1615778 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1443567 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1427186 (Python Code)

Max Activating Token Index: 878