Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 25 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.9051. Min Act: -0.0001

Data Index: 415536 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8690. Min Act: -0.0001

Data Index: 384861 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8838. Min Act: -0.0001

Data Index: 543779 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8882. Min Act: -0.0001

Data Index: 1150377 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8269. Min Act: -0.0001

Data Index: 1053788 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8253. Min Act: -0.0001

Data Index: 779695 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8446. Min Act: -0.0001

Data Index: 822647 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.9305. Min Act: -0.0001

Data Index: 102559 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8631. Min Act: -0.0001

Data Index: 693504 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8199. Min Act: -0.0001

Data Index: 193950 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1333266 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7642. Min Act: -0.0001

Data Index: 451001 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7882. Min Act: -0.0001

Data Index: 1193176 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7322. Min Act: -0.0001

Data Index: 37837 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7571. Min Act: -0.0001

Data Index: 323888 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8147. Min Act: -0.0001

Data Index: 608705 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8131. Min Act: -0.0001

Data Index: 481703 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.6938. Min Act: -0.0001

Data Index: 371759 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7840. Min Act: -0.0001

Data Index: 968074 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7505. Min Act: -0.0001

Data Index: 650115 (C4 (Web Text))

Max Activating Token Index: 853