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

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

Neuron 2478 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.2451. Min Act: -0.0002

Data Index: 1546737 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.1758. Min Act: -0.0002

Data Index: 1601448 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.1120. Min Act: -0.0002

Data Index: 1499796 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0842. Min Act: -0.0002

Data Index: 1410107 (Python Code)

Max Activating Token Index: 810

Text #4

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0789. Min Act: -0.0002

Data Index: 1554937 (Python Code)

Max Activating Token Index: 758

Text #5

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0706. Min Act: -0.0002

Data Index: 1379523 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0590. Min Act: -0.0002

Data Index: 1363032 (Python Code)

Max Activating Token Index: 446

Text #7

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0603. Min Act: -0.0002

Data Index: 1549968 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0438. Min Act: -0.0002

Data Index: 1445096 (Python Code)

Max Activating Token Index: 664

Text #9

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0518. Min Act: -0.0002

Data Index: 1642855 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0443. Min Act: -0.0002

Data Index: 1494850 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0354. Min Act: -0.0002

Data Index: 1430708 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0405. Min Act: -0.0002

Data Index: 1559560 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0219. Min Act: -0.0002

Data Index: 1451344 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0364. Min Act: -0.0002

Data Index: 1641375 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0090. Min Act: -0.0002

Data Index: 1360723 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0243. Min Act: -0.0002

Data Index: 1596382 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0118. Min Act: -0.0002

Data Index: 1608416 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 1.2451. Min Range: -1.2451

Max Act: 0.9959. Min Act: -0.0002

Data Index: 1406527 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 1.2451. Min Range: -1.2451

Max Act: 1.0163. Min Act: -0.0002

Data Index: 1421932 (Python Code)

Max Activating Token Index: 851