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

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

Neuron 85 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: 0.9287. Min Range: -0.9287

Max Act: 0.9205. Min Act: -0.0000

Data Index: 954450 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8870. Min Act: -0.0000

Data Index: 484833 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8655. Min Act: -0.0000

Data Index: 514964 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8834. Min Act: -0.0000

Data Index: 259808 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8868. Min Act: -0.0000

Data Index: 562391 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8394. Min Act: -0.0000

Data Index: 12083 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8734. Min Act: -0.0000

Data Index: 228438 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1223756 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1333789 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8391. Min Act: -0.0000

Data Index: 147384 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8153. Min Act: -0.0000

Data Index: 54839 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8689. Min Act: -0.0000

Data Index: 444077 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1357661 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1006907 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.8387. Min Act: -0.0000

Data Index: 544101 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7427. Min Act: -0.0000

Data Index: 778927 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1044951 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7212. Min Act: -0.0000

Data Index: 947107 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7294. Min Act: -0.0000

Data Index: 889543 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7811. Min Act: -0.0000

Data Index: 307947 (C4 (Web Text))

Max Activating Token Index: 1022