Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 559 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1001. Min Act: -0.0000

Data Index: 231555 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1077257 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1060. Min Act: -0.0000

Data Index: 415592 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1073. Min Act: -0.0000

Data Index: 216028 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1070. Min Act: -0.0000

Data Index: 935535 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1005. Min Act: -0.0000

Data Index: 217064 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0924. Min Act: -0.0000

Data Index: 326123 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0879. Min Act: -0.0000

Data Index: 790776 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0940. Min Act: -0.0000

Data Index: 665446 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1128175 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1034755 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0853. Min Act: -0.0000

Data Index: 149865 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0810. Min Act: -0.0000

Data Index: 705161 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0773. Min Act: -0.0000

Data Index: 558125 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1300891 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1326419 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0700. Min Act: -0.0000

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0691. Min Act: -0.0000

Data Index: 847116 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1012242 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1411520 (Python Code)

Max Activating Token Index: 999