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

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

Neuron 3245 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: 5.4903. Min Range: -5.4903

Max Act: 5.4300. Min Act: -0.0000

Data Index: 1576065 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.2469. Min Act: -0.0000

Data Index: 1392812 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.1053. Min Act: -0.0000

Data Index: 1592842 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 5.4903. Min Range: -5.4903

Max Act: 4.9760. Min Act: -0.0000

Data Index: 1652032 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.3389. Min Act: -0.0000

Data Index: 1384552 (Python Code)

Max Activating Token Index: 960

Text #5

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.1092. Min Act: -0.0000

Data Index: 1573613 (Python Code)

Max Activating Token Index: 669

Text #6

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.2712. Min Act: -0.0000

Data Index: 1418873 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.2916. Min Act: -0.0000

Data Index: 1491432 (Python Code)

Max Activating Token Index: 633

Text #8

Max Range: 5.4903. Min Range: -5.4903

Max Act: 4.9596. Min Act: -0.0000

Data Index: 1538726 (Python Code)

Max Activating Token Index: 494

Text #9

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.2276. Min Act: -0.0000

Data Index: 1528913 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.0464. Min Act: -0.0000

Data Index: 1391661 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.0519. Min Act: -0.0000

Data Index: 1379098 (Python Code)

Max Activating Token Index: 291

Text #12

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.1953. Min Act: -0.0000

Data Index: 1519730 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 5.4903. Min Range: -5.4903

Max Act: 4.8047. Min Act: -0.0000

Data Index: 1638680 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.4903. Min Act: -0.0000

Data Index: 1458802 (Python Code)

Max Activating Token Index: 937

Text #15

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.2679. Min Act: -0.0000

Data Index: 1533654 (Python Code)

Max Activating Token Index: 719

Text #16

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.0700. Min Act: -0.0000

Data Index: 1622414 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.0316. Min Act: -0.0000

Data Index: 1580052 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 5.4903. Min Range: -5.4903

Max Act: 5.0381. Min Act: -0.0000

Data Index: 1551979 (Python Code)

Max Activating Token Index: 586

Text #19

Max Range: 5.4903. Min Range: -5.4903

Max Act: 4.7276. Min Act: -0.0000

Data Index: 1441966 (Python Code)

Max Activating Token Index: 150