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

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

Neuron 711 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.9026. Min Act: -0.0000

Data Index: 3458 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.9077. Min Act: -0.0001

Data Index: 535732 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 2.0043. Min Range: -2.0043

Max Act: 2.0043. Min Act: -0.0001

Data Index: 826901 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.5311. Min Act: -0.0000

Data Index: 140683 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.7131. Min Act: -0.0001

Data Index: 1253002 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.7769. Min Act: -0.0000

Data Index: 28093 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6864. Min Act: -0.0001

Data Index: 315901 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.9212. Min Act: -0.0001

Data Index: 1204267 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6729. Min Act: -0.0000

Data Index: 1235713 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6762. Min Act: -0.0001

Data Index: 1019216 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.8008. Min Act: -0.0000

Data Index: 1309955 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6430. Min Act: -0.0000

Data Index: 20262 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6936. Min Act: -0.0001

Data Index: 696887 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.7368. Min Act: -0.0001

Data Index: 435895 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6024. Min Act: -0.0001

Data Index: 1215715 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6418. Min Act: -0.0000

Data Index: 131597 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.9253. Min Act: -0.0000

Data Index: 842925 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6360. Min Act: -0.0000

Data Index: 584090 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.6190. Min Act: -0.0001

Data Index: 471133 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 2.0043. Min Range: -2.0043

Max Act: 1.7268. Min Act: -0.0001

Data Index: 1007842 (C4 (Web Text))

Max Activating Token Index: 917