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

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

Neuron 5176 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7401. Min Act: -0.0003

Data Index: 1005281 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7102. Min Act: -0.0002

Data Index: 730742 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7161. Min Act: -0.0002

Data Index: 794736 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7140. Min Act: -0.0002

Data Index: 908437 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7117. Min Act: -0.0002

Data Index: 1272849 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6751. Min Act: -0.0002

Data Index: 559923 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6794. Min Act: -0.0002

Data Index: 90030 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6760. Min Act: -0.0002

Data Index: 899057 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6829. Min Act: -0.0002

Data Index: 704694 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6762. Min Act: -0.0002

Data Index: 204687 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6769. Min Act: -0.0003

Data Index: 524991 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6794. Min Act: -0.0002

Data Index: 799761 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6806. Min Act: -0.0002

Data Index: 756400 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6574. Min Act: -0.0002

Data Index: 650156 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6580. Min Act: -0.0002

Data Index: 1089511 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6698. Min Act: -0.0002

Data Index: 218891 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6564. Min Act: -0.0002

Data Index: 1035324 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6451. Min Act: -0.0002

Data Index: 906032 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6562. Min Act: -0.0002

Data Index: 1166260 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6522. Min Act: -0.0002

Data Index: 448561 (C4 (Web Text))

Max Activating Token Index: 227