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

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

Neuron 784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1268. Min Act: -0.0002

Data Index: 566274 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1097. Min Act: -0.0002

Data Index: 66780 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1340536 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1013457 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0983. Min Act: -0.0002

Data Index: 913810 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0964. Min Act: -0.0002

Data Index: 616967 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0937. Min Act: -0.0002

Data Index: 390497 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0959. Min Act: -0.0002

Data Index: 383410 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0904. Min Act: -0.0002

Data Index: 671715 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0938. Min Act: -0.0002

Data Index: 385424 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0878. Min Act: -0.0002

Data Index: 371664 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0911. Min Act: -0.0002

Data Index: 444528 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0856. Min Act: -0.0002

Data Index: 870618 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0814. Min Act: -0.0002

Data Index: 827109 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1127335 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1058036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0773. Min Act: -0.0002

Data Index: 187338 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1259977 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1069905 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0770. Min Act: -0.0002

Data Index: 54768 (C4 (Web Text))

Max Activating Token Index: 812