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

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

Neuron 5148 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.4058. Min Act: -0.0000

Data Index: 1449850 (Python Code)

Max Activating Token Index: 702

Text #1

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.1758. Min Act: -0.0000

Data Index: 1386563 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.1342. Min Act: -0.0000

Data Index: 1517869 (Python Code)

Max Activating Token Index: 760

Text #3

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1490357 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.1980. Min Act: -0.0000

Data Index: 1585797 (Python Code)

Max Activating Token Index: 968

Text #5

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9923. Min Act: -0.0000

Data Index: 1644475 (Python Code)

Max Activating Token Index: 864

Text #6

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9638. Min Act: -0.0000

Data Index: 1384626 (Python Code)

Max Activating Token Index: 306

Text #7

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.0844. Min Act: -0.0000

Data Index: 1619437 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.0790. Min Act: -0.0000

Data Index: 1528827 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.1674. Min Act: -0.0000

Data Index: 1411478 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.1474. Min Act: -0.0000

Data Index: 1486658 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9098. Min Act: -0.0000

Data Index: 1529526 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9092. Min Act: -0.0000

Data Index: 1445716 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1579983 (Python Code)

Max Activating Token Index: 571

Text #14

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.8086. Min Act: -0.0000

Data Index: 1629291 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 2.4058. Min Range: -2.4058

Max Act: 2.0919. Min Act: -0.0000

Data Index: 1621210 (Python Code)

Max Activating Token Index: 990

Text #16

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9050. Min Act: -0.0000

Data Index: 1652437 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9779. Min Act: -0.0000

Data Index: 1455828 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1478778 (Python Code)

Max Activating Token Index: 512

Text #19

Max Range: 2.4058. Min Range: -2.4058

Max Act: 1.9852. Min Act: -0.0000

Data Index: 1382596 (Python Code)

Max Activating Token Index: 383