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

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

Neuron 2325 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0778. Min Act: -0.0002

Data Index: 708157 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1181244 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1310424 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0747. Min Act: -0.0002

Data Index: 903085 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0728. Min Act: -0.0002

Data Index: 635457 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0636. Min Act: -0.0002

Data Index: 10694 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1145476 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0683. Min Act: -0.0002

Data Index: 444775 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0673. Min Act: -0.0002

Data Index: 135669 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0644. Min Act: -0.0002

Data Index: 236852 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0654. Min Act: -0.0002

Data Index: 313687 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0648. Min Act: -0.0002

Data Index: 840743 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0662. Min Act: -0.0002

Data Index: 504040 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1083942 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1134416 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0654. Min Act: -0.0002

Data Index: 888750 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0643. Min Act: -0.0002

Data Index: 596705 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1157756 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0645. Min Act: -0.0002

Data Index: 649116 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1068469 (C4 (Web Text))

Max Activating Token Index: 796