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

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

Neuron 5837 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3654. Min Range: -5.3654

Max Act: 5.3654. Min Act: -0.0000

Data Index: 1322767 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 5.3654. Min Range: -5.3654

Max Act: 5.2075. Min Act: -0.0000

Data Index: 314587 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 5.3654. Min Range: -5.3654

Max Act: 5.0229. Min Act: -0.0000

Data Index: 711783 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.8994. Min Act: -0.0000

Data Index: 131655 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 5.3654. Min Range: -5.3654

Max Act: 5.0565. Min Act: -0.0000

Data Index: 471817 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 5.3654. Min Range: -5.3654

Max Act: 5.2164. Min Act: -0.0000

Data Index: 1351261 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.8938. Min Act: -0.0000

Data Index: 433428 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.8857. Min Act: -0.0000

Data Index: 1207105 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.8772. Min Act: -0.0000

Data Index: 19830 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.8549. Min Act: -0.0000

Data Index: 90531 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.7013. Min Act: -0.0000

Data Index: 1054826 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.6236. Min Act: -0.0000

Data Index: 1131502 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.6350. Min Act: -0.0000

Data Index: 742643 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.3741. Min Act: -0.0000

Data Index: 44669 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.5792. Min Act: -0.0000

Data Index: 1141001 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.5733. Min Act: -0.0000

Data Index: 989712 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.3236. Min Act: -0.0000

Data Index: 319915 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.2800. Min Act: -0.0000

Data Index: 244278 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.4013. Min Act: -0.0000

Data Index: 1098012 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 5.3654. Min Range: -5.3654

Max Act: 4.3985. Min Act: -0.0000

Data Index: 622850 (C4 (Web Text))

Max Activating Token Index: 979