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

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

Neuron 3950 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1163714 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4838. Min Act: -0.0000

Data Index: 332225 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4997. Min Act: -0.0000

Data Index: 756621 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1143082 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4436. Min Act: -0.0000

Data Index: 88532 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1129821 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4287. Min Act: -0.0000

Data Index: 422594 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1270042 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4256. Min Act: -0.0000

Data Index: 579412 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1186279 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1139320 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1006126 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4121. Min Act: -0.0000

Data Index: 621853 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.3887. Min Act: -0.0000

Data Index: 168481 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1106811 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.3889. Min Act: -0.0000

Data Index: 607839 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.3860. Min Act: -0.0000

Data Index: 634048 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4012. Min Act: -0.0000

Data Index: 433558 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1075775 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.3864. Min Act: -0.0000

Data Index: 451834 (C4 (Web Text))

Max Activating Token Index: 26