Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1174 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0042. Min Act: -0.0005

Data Index: 556200 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0037. Min Act: -0.0005

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1481823 (Python Code)

Max Activating Token Index: 921

Text #3

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0027. Min Act: -0.0005

Data Index: 1600010 (Python Code)

Max Activating Token Index: 801

Text #4

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0028. Min Act: -0.0005

Data Index: 1361804 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0027. Min Act: -0.0005

Data Index: 1411485 (Python Code)

Max Activating Token Index: 677

Text #6

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0026. Min Act: -0.0005

Data Index: 1372628 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1529210 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1568294 (Python Code)

Max Activating Token Index: 659

Text #9

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0024. Min Act: -0.0005

Data Index: 1501364 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0024. Min Act: -0.0005

Data Index: 1530738 (Python Code)

Max Activating Token Index: 722

Text #11

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0024. Min Act: -0.0005

Data Index: 1466773 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0024. Min Act: -0.0005

Data Index: 1464231 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0023. Min Act: -0.0005

Data Index: 936501 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0023. Min Act: -0.0005

Data Index: 1608321 (Python Code)

Max Activating Token Index: 703

Text #15

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0023. Min Act: -0.0005

Data Index: 1544516 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0023. Min Act: -0.0005

Data Index: 1414283 (Python Code)

Max Activating Token Index: 721

Text #17

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0023. Min Act: -0.0005

Data Index: 1475682 (Python Code)

Max Activating Token Index: 656

Text #18

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0023. Min Act: -0.0005

Data Index: 1486185 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0022. Min Act: -0.0005

Data Index: 1228954 (C4 (Web Text))

Max Activating Token Index: 744