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

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

Neuron 950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1350. Min Act: -0.0001

Data Index: 985473 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1284. Min Act: -0.0001

Data Index: 981705 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1129. Min Act: -0.0001

Data Index: 570843 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1100. Min Act: -0.0001

Data Index: 871469 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1095. Min Act: -0.0001

Data Index: 833809 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1095. Min Act: -0.0001

Data Index: 256790 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1031. Min Act: -0.0001

Data Index: 816730 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1146. Min Act: -0.0001

Data Index: 673674 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1182895 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1027. Min Act: -0.0001

Data Index: 674993 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1287539 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1027407 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0881. Min Act: -0.0001

Data Index: 703020 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0986. Min Act: -0.0001

Data Index: 572925 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0976. Min Act: -0.0001

Data Index: 78330 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1002. Min Act: -0.0001

Data Index: 34101 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0922. Min Act: -0.0001

Data Index: 318156 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0961. Min Act: -0.0001

Data Index: 654487 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1231816 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0949. Min Act: -0.0001

Data Index: 212158 (C4 (Web Text))

Max Activating Token Index: 743