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

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

Neuron 2898 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: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0001

Data Index: 145235 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1091651 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1299. Min Act: -0.0001

Data Index: 285620 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1357. Min Act: -0.0001

Data Index: 262276 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1379. Min Act: -0.0001

Data Index: 887443 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1245. Min Act: -0.0001

Data Index: 560120 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1259. Min Act: -0.0001

Data Index: 178786 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1116. Min Act: -0.0001

Data Index: 894049 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1048. Min Act: -0.0001

Data Index: 317759 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1041. Min Act: -0.0001

Data Index: 377261 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1299147 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1325136 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1018. Min Act: -0.0001

Data Index: 831696 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1061. Min Act: -0.0001

Data Index: 525519 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1143609 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1031. Min Act: -0.0001

Data Index: 489212 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1024. Min Act: -0.0001

Data Index: 20023 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1012. Min Act: -0.0001

Data Index: 610796 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0867. Min Act: -0.0001

Data Index: 996884 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1006. Min Act: -0.0001

Data Index: 643681 (C4 (Web Text))

Max Activating Token Index: 688