Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2734 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0001

Data Index: 426776 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1010. Min Act: -0.0001

Data Index: 601059 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1164800 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0911. Min Act: -0.0001

Data Index: 512811 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0884. Min Act: -0.0001

Data Index: 946813 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1288511 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1333431 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0873. Min Act: -0.0001

Data Index: 324837 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0895. Min Act: -0.0001

Data Index: 572654 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0885. Min Act: -0.0001

Data Index: 941662 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0902. Min Act: -0.0001

Data Index: 646160 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1157191 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0795. Min Act: -0.0001

Data Index: 908763 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1196916 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0823. Min Act: -0.0001

Data Index: 423086 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0853. Min Act: -0.0001

Data Index: 234893 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0850. Min Act: -0.0001

Data Index: 655936 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1016399 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0753. Min Act: -0.0001

Data Index: 892683 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1341516 (C4 (Web Text))

Max Activating Token Index: 880