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

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

Neuron 2599 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.7742. Min Range: -8.7742

Max Act: 8.7742. Min Act: -0.0000

Data Index: 1044059 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 8.7742. Min Range: -8.7742

Max Act: 8.4767. Min Act: -0.0000

Data Index: 940356 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 8.7742. Min Range: -8.7742

Max Act: 8.1212. Min Act: -0.0000

Data Index: 1176345 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.9400. Min Act: -0.0000

Data Index: 721308 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 8.7742. Min Range: -8.7742

Max Act: 8.0518. Min Act: -0.0000

Data Index: 261707 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.8347. Min Act: -0.0000

Data Index: 558386 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.8308. Min Act: -0.0000

Data Index: 652036 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.9038. Min Act: -0.0000

Data Index: 1051570 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.8707. Min Act: -0.0000

Data Index: 1357678 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.8468. Min Act: -0.0000

Data Index: 250164 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.3736. Min Act: -0.0000

Data Index: 130626 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.2925. Min Act: 0.0002

Data Index: 961974 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.8462. Min Act: -0.0000

Data Index: 525445 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.8666. Min Act: -0.0000

Data Index: 824925 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.2186. Min Act: -0.0000

Data Index: 1336034 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.7495. Min Act: -0.0000

Data Index: 403751 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.3010. Min Act: -0.0000

Data Index: 1137945 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.4971. Min Act: -0.0000

Data Index: 712766 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 8.7742. Min Range: -8.7742

Max Act: 8.0476. Min Act: -0.0000

Data Index: 656017 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 8.7742. Min Range: -8.7742

Max Act: 7.3257. Min Act: -0.0000

Data Index: 211692 (C4 (Web Text))

Max Activating Token Index: 436