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

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

Neuron 2061 in Layer 0

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: 0.9668. Min Range: -0.9668

Max Act: 0.9668. Min Act: -0.0001

Data Index: 1479550 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9505. Min Act: -0.0001

Data Index: 1517910 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9281. Min Act: -0.0001

Data Index: 1458450 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8975. Min Act: -0.0001

Data Index: 1378511 (Python Code)

Max Activating Token Index: 651

Text #4

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8366. Min Act: -0.0001

Data Index: 1411622 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1574527 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8348. Min Act: -0.0001

Data Index: 1449584 (Python Code)

Max Activating Token Index: 266

Text #7

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1410337 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8134. Min Act: -0.0001

Data Index: 1386799 (Python Code)

Max Activating Token Index: 506

Text #9

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1558552 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1495110 (Python Code)

Max Activating Token Index: 878

Text #11

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7885. Min Act: -0.0001

Data Index: 1491619 (Python Code)

Max Activating Token Index: 763

Text #12

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1417734 (Python Code)

Max Activating Token Index: 572

Text #13

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7644. Min Act: -0.0002

Data Index: 1640627 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7488. Min Act: -0.0002

Data Index: 1518479 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1377726 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7472. Min Act: -0.0001

Data Index: 1432543 (Python Code)

Max Activating Token Index: 519

Text #17

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7536. Min Act: -0.0001

Data Index: 1573755 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7456. Min Act: -0.0001

Data Index: 1447145 (Python Code)

Max Activating Token Index: 907

Text #19

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1564280 (Python Code)

Max Activating Token Index: 939