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

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

Neuron 1875 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1170859 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1029787 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3621. Min Act: -0.0000

Data Index: 466342 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4292. Min Act: -0.0000

Data Index: 185749 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4271. Min Act: -0.0000

Data Index: 557260 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4079. Min Act: -0.0000

Data Index: 820104 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3722. Min Act: -0.0000

Data Index: 212751 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1169185 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1090732 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1087185 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4144. Min Act: -0.0000

Data Index: 401241 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4035. Min Act: -0.0000

Data Index: 642203 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3854. Min Act: -0.0000

Data Index: 559485 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1050255 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1313499 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1144795 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4022. Min Act: -0.0000

Data Index: 406287 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4197. Min Act: -0.0000

Data Index: 51035 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4180. Min Act: -0.0000

Data Index: 791933 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3758. Min Act: -0.0000

Data Index: 52129 (C4 (Web Text))

Max Activating Token Index: 843