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

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

Neuron 1293 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1275788 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1062. Min Act: -0.0001

Data Index: 149513 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0990. Min Act: -0.0001

Data Index: 498200 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0806. Min Act: -0.0001

Data Index: 624122 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0793. Min Act: -0.0001

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1350930 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0803. Min Act: -0.0001

Data Index: 969315 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1142528 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1317763 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0753. Min Act: -0.0001

Data Index: 866943 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1157520 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0699. Min Act: -0.0001

Data Index: 848191 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0712. Min Act: -0.0001

Data Index: 150397 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0721. Min Act: -0.0001

Data Index: 165547 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0738. Min Act: -0.0001

Data Index: 642275 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0734. Min Act: -0.0001

Data Index: 718359 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1172086 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0757. Min Act: -0.0001

Data Index: 891308 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0700. Min Act: -0.0001

Data Index: 164673 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0739. Min Act: -0.0001

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 658