Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0766. Min Range: -1.0766

Max Act: 1.0766. Min Act: -0.0001

Data Index: 595289 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 1.0766. Min Range: -1.0766

Max Act: 1.0014. Min Act: -0.0001

Data Index: 1290659 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9667. Min Act: -0.0001

Data Index: 1191638 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9040. Min Act: -0.0001

Data Index: 822788 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9528. Min Act: -0.0001

Data Index: 74711 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9838. Min Act: -0.0001

Data Index: 368185 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8918. Min Act: -0.0001

Data Index: 1091832 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9386. Min Act: -0.0001

Data Index: 163502 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1307273 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9606. Min Act: -0.0001

Data Index: 1289085 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9862. Min Act: -0.0001

Data Index: 158685 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8376. Min Act: -0.0001

Data Index: 677792 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9217. Min Act: -0.0001

Data Index: 1024415 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.0766. Min Range: -1.0766

Max Act: 1.0084. Min Act: -0.0001

Data Index: 304730 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8708. Min Act: -0.0001

Data Index: 417364 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9082. Min Act: -0.0001

Data Index: 1196007 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8796. Min Act: -0.0001

Data Index: 123518 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8806. Min Act: -0.0001

Data Index: 1057093 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8755. Min Act: -0.0001

Data Index: 555444 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9296. Min Act: -0.0001

Data Index: 1312959 (C4 (Web Text))

Max Activating Token Index: 864