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

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

Neuron 2916 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1497694 (Python Code)

Max Activating Token Index: 534

Text #1

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1490168 (Python Code)

Max Activating Token Index: 730

Text #2

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1591439 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1565695 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1538519 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1372775 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1415071 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1574269 (Python Code)

Max Activating Token Index: 554

Text #8

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1481366 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1654562 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1399854 (Python Code)

Max Activating Token Index: 529

Text #11

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1454777 (Python Code)

Max Activating Token Index: 839

Text #12

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1630506 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1558555 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1429114 (Python Code)

Max Activating Token Index: 462

Text #15

Max Range: 1.3752. Min Range: -1.3752

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1516453 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9399. Min Act: -0.0001

Data Index: 1532772 (Python Code)

Max Activating Token Index: 344

Text #17

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1437503 (Python Code)

Max Activating Token Index: 143

Text #18

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1452904 (Python Code)

Max Activating Token Index: 980

Text #19

Max Range: 1.3752. Min Range: -1.3752

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1466083 (Python Code)

Max Activating Token Index: 41