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

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

Neuron 3043 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1315515 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1217. Min Act: -0.0000

Data Index: 247702 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1380. Min Act: -0.0000

Data Index: 655433 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1115. Min Act: -0.0000

Data Index: 835712 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1197. Min Act: -0.0000

Data Index: 946530 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.0902. Min Act: -0.0000

Data Index: 662176 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1067. Min Act: -0.0000

Data Index: 707037 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.0852. Min Act: -0.0000

Data Index: 750696 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.0947. Min Act: -0.0000

Data Index: 982475 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1628402 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1241686 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1002. Min Act: -0.0000

Data Index: 642278 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1047. Min Act: -0.0000

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1440492 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1066. Min Act: -0.0000

Data Index: 813623 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1110. Min Act: -0.0000

Data Index: 621759 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.0953. Min Act: -0.0000

Data Index: 600843 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.0994. Min Act: -0.0000

Data Index: 40450 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1030. Min Act: -0.0000

Data Index: 354768 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1020. Min Act: -0.0000

Data Index: 260494 (C4 (Web Text))

Max Activating Token Index: 620