Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0005

Data Index: 1139994 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1113. Min Act: -0.0005

Data Index: 1154848 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1102. Min Act: -0.0005

Data Index: 955571 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1068. Min Act: -0.0005

Data Index: 1213122 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1020. Min Act: -0.0005

Data Index: 1053552 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1017. Min Act: -0.0005

Data Index: 869604 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0909. Min Act: -0.0005

Data Index: 1115863 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0966. Min Act: -0.0005

Data Index: 1160909 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0969. Min Act: -0.0005

Data Index: 1178918 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0995. Min Act: -0.0005

Data Index: 215015 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0950. Min Act: -0.0005

Data Index: 753637 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0935. Min Act: -0.0005

Data Index: 974356 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0863. Min Act: -0.0005

Data Index: 391637 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0902. Min Act: -0.0005

Data Index: 1315188 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0882. Min Act: -0.0005

Data Index: 66660 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0831. Min Act: -0.0005

Data Index: 689753 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0990. Min Act: -0.0005

Data Index: 601976 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0891. Min Act: -0.0005

Data Index: 599558 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0872. Min Act: -0.0005

Data Index: 408452 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0922. Min Act: -0.0005

Data Index: 889502 (C4 (Web Text))

Max Activating Token Index: 208