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

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

Neuron 678 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2394. Min Range: -2.2394

Max Act: 2.2394. Min Act: -0.0000

Data Index: 936679 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 2.2394. Min Range: -2.2394

Max Act: 2.1004. Min Act: -0.0000

Data Index: 1310609 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 2.2394. Min Range: -2.2394

Max Act: 2.0167. Min Act: -0.0000

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 2.2394. Min Range: -2.2394

Max Act: 2.0115. Min Act: -0.0000

Data Index: 1046791 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.9838. Min Act: -0.0000

Data Index: 293731 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.8718. Min Act: -0.0000

Data Index: 1139988 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.9640. Min Act: -0.0000

Data Index: 649606 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.9197. Min Act: -0.0000

Data Index: 11848 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.8968. Min Act: -0.0000

Data Index: 1280110 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.8975. Min Act: -0.0000

Data Index: 81008 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.8670. Min Act: -0.0000

Data Index: 648673 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.7149. Min Act: -0.0000

Data Index: 772163 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.8048. Min Act: -0.0000

Data Index: 819780 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.7857. Min Act: -0.0000

Data Index: 192326 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.7855. Min Act: 0.0000

Data Index: 594564 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.7886. Min Act: -0.0000

Data Index: 589897 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.8020. Min Act: -0.0000

Data Index: 323510 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.7380. Min Act: -0.0000

Data Index: 990829 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.6463. Min Act: -0.0000

Data Index: 748197 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 2.2394. Min Range: -2.2394

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1332964 (C4 (Web Text))

Max Activating Token Index: 758