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

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

Neuron 1622 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0001

Data Index: 642976 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1037142 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0754. Min Act: -0.0001

Data Index: 878586 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0759. Min Act: -0.0001

Data Index: 516717 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0794. Min Act: -0.0001

Data Index: 600908 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0661. Min Act: -0.0001

Data Index: 556561 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0670. Min Act: -0.0001

Data Index: 680948 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1380867 (Python Code)

Max Activating Token Index: 803

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0664. Min Act: -0.0001

Data Index: 309090 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1327918 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0621. Min Act: -0.0001

Data Index: 435245 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0590. Min Act: -0.0001

Data Index: 269148 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0625. Min Act: -0.0001

Data Index: 339918 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0628. Min Act: -0.0001

Data Index: 66336 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1037231 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0626. Min Act: -0.0001

Data Index: 715062 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0623. Min Act: -0.0001

Data Index: 30439 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0664. Min Act: -0.0001

Data Index: 747553 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0658. Min Act: -0.0001

Data Index: 109595 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0683. Min Act: -0.0001

Data Index: 9296 (C4 (Web Text))

Max Activating Token Index: 966