Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 801 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.2905. Min Act: -0.0000

Data Index: 948629 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.1876. Min Act: -0.0000

Data Index: 664403 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.1569. Min Act: -0.0000

Data Index: 372746 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.2029. Min Act: -0.0000

Data Index: 854871 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1516111 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9765. Min Act: -0.0000

Data Index: 410626 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.0350. Min Act: -0.0000

Data Index: 610133 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1534250 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1606620 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1480753 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 1.2905. Min Range: -1.2905

Max Act: 1.0131. Min Act: -0.0000

Data Index: 843076 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9353. Min Act: -0.0000

Data Index: 809770 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9164. Min Act: -0.0000

Data Index: 679095 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1315890 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9612. Min Act: -0.0000

Data Index: 633644 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1436017 (Python Code)

Max Activating Token Index: 602

Text #16

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1646193 (Python Code)

Max Activating Token Index: 801

Text #17

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.8841. Min Act: -0.0000

Data Index: 731738 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1435925 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 1.2905. Min Range: -1.2905

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1540038 (Python Code)

Max Activating Token Index: 141