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

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

Neuron 678 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0000

Data Index: 595376 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0843. Min Act: -0.0000

Data Index: 216231 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1583626 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0787. Min Act: -0.0001

Data Index: 729376 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1251584 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0768. Min Act: -0.0000

Data Index: 733520 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0773. Min Act: -0.0000

Data Index: 774584 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0825. Min Act: -0.0000

Data Index: 198729 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0711. Min Act: -0.0000

Data Index: 58791 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1145465 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0731. Min Act: -0.0000

Data Index: 293939 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1343848 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0693. Min Act: -0.0000

Data Index: 854701 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0743. Min Act: -0.0000

Data Index: 299262 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0742. Min Act: -0.0000

Data Index: 970496 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1289902 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0696. Min Act: -0.0000

Data Index: 420204 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0588. Min Act: -0.0000

Data Index: 877103 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1030768 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0717. Min Act: -0.0000

Data Index: 546676 (C4 (Web Text))

Max Activating Token Index: 252