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

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

Neuron 3902 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: 0.7827. Min Range: -0.7827

Max Act: 0.7827. Min Act: -0.0000

Data Index: 429175 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6938. Min Act: -0.0000

Data Index: 378421 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6500. Min Act: -0.0000

Data Index: 289692 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6878. Min Act: -0.0000

Data Index: 984330 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5944. Min Act: -0.0000

Data Index: 359007 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6229. Min Act: -0.0000

Data Index: 85622 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5588. Min Act: -0.0000

Data Index: 342927 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1051076 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5984. Min Act: -0.0000

Data Index: 593886 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5408. Min Act: -0.0000

Data Index: 659812 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5550. Min Act: -0.0000

Data Index: 731454 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5136. Min Act: -0.0000

Data Index: 430848 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5305. Min Act: -0.0000

Data Index: 223925 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5453. Min Act: -0.0000

Data Index: 560279 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1066007 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5653. Min Act: -0.0000

Data Index: 76018 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5146. Min Act: -0.0000

Data Index: 862713 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.4911. Min Act: -0.0000

Data Index: 852496 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5071. Min Act: -0.0000

Data Index: 417954 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5055. Min Act: -0.0000

Data Index: 359205 (C4 (Web Text))

Max Activating Token Index: 25