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

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

Neuron 5921 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: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0001

Data Index: 741521 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0861. Min Act: -0.0001

Data Index: 793731 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0830. Min Act: -0.0001

Data Index: 605733 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0853. Min Act: -0.0001

Data Index: 833600 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1416768 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0896. Min Act: -0.0001

Data Index: 578700 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0794. Min Act: -0.0001

Data Index: 138973 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0785. Min Act: -0.0001

Data Index: 758960 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1183162 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1293569 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1480115 (Python Code)

Max Activating Token Index: 874

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1091 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1238411 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0722. Min Act: -0.0001

Data Index: 58675 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1005498 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0735. Min Act: -0.0001

Data Index: 938367 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1391849 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0591. Min Act: -0.0001

Data Index: 491281 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0683. Min Act: -0.0001

Data Index: 346241 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0685. Min Act: -0.0001

Data Index: 84331 (C4 (Web Text))

Max Activating Token Index: 419