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

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

Neuron 5333 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.7012. Min Act: -0.0000

Data Index: 973565 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1155693 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6129. Min Act: -0.0000

Data Index: 189807 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6076. Min Act: -0.0000

Data Index: 774219 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5625. Min Act: -0.0000

Data Index: 59247 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5987. Min Act: -0.0000

Data Index: 943259 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6127. Min Act: -0.0000

Data Index: 126012 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6359. Min Act: -0.0000

Data Index: 616336 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1064101 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5636. Min Act: -0.0000

Data Index: 957243 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5846. Min Act: -0.0000

Data Index: 276874 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5860. Min Act: -0.0000

Data Index: 125176 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5692. Min Act: -0.0000

Data Index: 973875 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6222. Min Act: -0.0000

Data Index: 36541 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5634. Min Act: -0.0000

Data Index: 551940 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6090. Min Act: -0.0000

Data Index: 782782 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5215. Min Act: -0.0000

Data Index: 277920 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5515. Min Act: -0.0000

Data Index: 160933 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5506. Min Act: -0.0000

Data Index: 506150 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4817. Min Act: -0.0000

Data Index: 923357 (C4 (Web Text))

Max Activating Token Index: 111