Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3707 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3804. Min Act: -0.0000

Data Index: 76968 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3446. Min Act: -0.0000

Data Index: 787366 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3444. Min Act: -0.0000

Data Index: 333420 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3639. Min Act: -0.0000

Data Index: 532700 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1233642 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3594. Min Act: -0.0000

Data Index: 719787 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3255. Min Act: -0.0000

Data Index: 8780 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3198. Min Act: -0.0001

Data Index: 150209 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3166. Min Act: -0.0000

Data Index: 141709 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3513. Min Act: -0.0001

Data Index: 475612 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3023. Min Act: -0.0001

Data Index: 481490 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3027. Min Act: -0.0000

Data Index: 275362 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3223. Min Act: -0.0000

Data Index: 639267 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2917. Min Act: -0.0001

Data Index: 915397 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2698. Min Act: -0.0000

Data Index: 73114 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2772. Min Act: -0.0000

Data Index: 191975 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1036085 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1146202 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1303566 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1357225 (C4 (Web Text))

Max Activating Token Index: 583