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

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

Neuron 2661 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.6517. Min Act: -0.0000

Data Index: 1368576 (Python Code)

Max Activating Token Index: 134

Text #1

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1434703 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.6014. Min Act: -0.0000

Data Index: 1452894 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1587001 (Python Code)

Max Activating Token Index: 820

Text #4

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1655966 (Python Code)

Max Activating Token Index: 861

Text #5

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.4332. Min Act: -0.0000

Data Index: 1498431 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1362453 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.4003. Min Act: -0.0000

Data Index: 1642167 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1368770 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1508729 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1424868 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1541064 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1467653 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1578377 (Python Code)

Max Activating Token Index: 442

Text #14

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.3577. Min Act: -0.0000

Data Index: 1556634 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1458106 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1587729 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1637355 (Python Code)

Max Activating Token Index: 466

Text #18

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1593424 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1374998 (Python Code)

Max Activating Token Index: 532