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

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

Neuron 1742 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1027. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1204. Min Act: -0.0000

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1451199 (Python Code)

Max Activating Token Index: 455

Text #3

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0910. Min Act: -0.0000

Data Index: 841178 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0952. Min Act: -0.0000

Data Index: 470436 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0850. Min Act: -0.0000

Data Index: 71015 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0860. Min Act: -0.0000

Data Index: 906268 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0812. Min Act: -0.0000

Data Index: 937589 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0785. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1197195 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1372266 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1473038 (Python Code)

Max Activating Token Index: 450

Text #13

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1471124 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1301759 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0707. Min Act: -0.0000

Data Index: 905512 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1549229 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0662. Min Act: -0.0000

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1071085 (C4 (Web Text))

Max Activating Token Index: 153