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

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

Neuron 3297 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: 1.0599. Min Range: -1.0599

Max Act: 1.0599. Min Act: -0.0001

Data Index: 945831 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7987. Min Act: -0.0000

Data Index: 160559 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1002313 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7714. Min Act: -0.0001

Data Index: 164194 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7597. Min Act: -0.0000

Data Index: 743925 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6898. Min Act: -0.0001

Data Index: 748395 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7258. Min Act: -0.0001

Data Index: 1014337 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6998. Min Act: -0.0001

Data Index: 918977 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7021. Min Act: -0.0001

Data Index: 520862 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6415. Min Act: -0.0001

Data Index: 780064 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7704. Min Act: -0.0001

Data Index: 333051 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6533. Min Act: -0.0001

Data Index: 855003 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6494. Min Act: -0.0001

Data Index: 106561 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6251. Min Act: -0.0001

Data Index: 656339 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6229. Min Act: -0.0000

Data Index: 824993 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.5745. Min Act: -0.0000

Data Index: 747369 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6091. Min Act: -0.0000

Data Index: 260228 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6572. Min Act: -0.0001

Data Index: 55946 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.5633. Min Act: -0.0000

Data Index: 91360 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.6073. Min Act: -0.0000

Data Index: 959055 (C4 (Web Text))

Max Activating Token Index: 46