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

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

Neuron 653 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: 0.7478. Min Range: -0.7478

Max Act: 0.7427. Min Act: -0.0000

Data Index: 289011 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.7444. Min Act: -0.0000

Data Index: 781530 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.7097. Min Act: -0.0000

Data Index: 831676 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.7478. Min Act: -0.0000

Data Index: 908507 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6807. Min Act: -0.0000

Data Index: 467011 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6913. Min Act: -0.0000

Data Index: 462051 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6498. Min Act: -0.0000

Data Index: 874879 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6040. Min Act: -0.0000

Data Index: 861258 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5557. Min Act: -0.0000

Data Index: 983305 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5284. Min Act: -0.0000

Data Index: 545246 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5156. Min Act: -0.0000

Data Index: 872754 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5037. Min Act: -0.0000

Data Index: 914530 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4885. Min Act: -0.0000

Data Index: 731015 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5136. Min Act: -0.0000

Data Index: 904189 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1013185 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4667. Min Act: -0.0000

Data Index: 413714 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4877. Min Act: -0.0000

Data Index: 746788 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1305417 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4863. Min Act: -0.0000

Data Index: 209908 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4701. Min Act: -0.0000

Data Index: 116084 (C4 (Web Text))

Max Activating Token Index: 493