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

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

Neuron 2824 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4937. Min Act: -0.0000

Data Index: 634635 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1188712 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4476. Min Act: -0.0000

Data Index: 522913 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4399. Min Act: 0.0002

Data Index: 599994 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4338. Min Act: 0.0000

Data Index: 162005 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4352. Min Act: -0.0000

Data Index: 792013 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4155. Min Act: -0.0000

Data Index: 478237 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1075194 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4044. Min Act: 0.0002

Data Index: 838965 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4040. Min Act: -0.0000

Data Index: 337110 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1018231 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3772. Min Act: -0.0000

Data Index: 4775 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3859. Min Act: -0.0000

Data Index: 194195 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3813. Min Act: -0.0000

Data Index: 404220 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3706. Min Act: -0.0000

Data Index: 575602 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3751. Min Act: -0.0000

Data Index: 211549 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3728. Min Act: -0.0000

Data Index: 547806 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1069984 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3741. Min Act: 0.0000

Data Index: 98160 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3767. Min Act: -0.0000

Data Index: 465276 (C4 (Web Text))

Max Activating Token Index: 490