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

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

Neuron 4229 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7084. Min Act: -0.0000

Data Index: 444853 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1298580 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6736. Min Act: -0.0000

Data Index: 384675 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1148215 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6380. Min Act: 0.0000

Data Index: 512484 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5940. Min Act: -0.0000

Data Index: 843472 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6281. Min Act: -0.0000

Data Index: 259726 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6251. Min Act: -0.0000

Data Index: 636744 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6261. Min Act: -0.0000

Data Index: 374047 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6004. Min Act: -0.0000

Data Index: 783012 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6082. Min Act: -0.0000

Data Index: 309794 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6016. Min Act: -0.0000

Data Index: 271168 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1138050 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5881. Min Act: -0.0000

Data Index: 496218 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5868. Min Act: -0.0000

Data Index: 848862 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5832. Min Act: -0.0000

Data Index: 237303 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5772. Min Act: -0.0000

Data Index: 887686 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5924. Min Act: -0.0000

Data Index: 967124 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1329102 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5598. Min Act: -0.0000

Data Index: 461012 (C4 (Web Text))

Max Activating Token Index: 415