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

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

Neuron 3345 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9881. Min Act: -0.0000

Data Index: 61462 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9694. Min Act: -0.0000

Data Index: 21935 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9318. Min Act: -0.0000

Data Index: 508777 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9278. Min Act: -0.0000

Data Index: 915137 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9503. Min Act: -0.0000

Data Index: 72805 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1314907 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1275674 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8878. Min Act: -0.0000

Data Index: 673253 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9002. Min Act: -0.0000

Data Index: 44421 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8761. Min Act: -0.0000

Data Index: 667848 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8465. Min Act: -0.0000

Data Index: 721467 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8948. Min Act: -0.0000

Data Index: 260633 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1055740 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8388. Min Act: -0.0000

Data Index: 440091 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1168730 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8558. Min Act: -0.0000

Data Index: 418249 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8761. Min Act: -0.0000

Data Index: 201726 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8436. Min Act: -0.0000

Data Index: 55783 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1170406 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8140. Min Act: -0.0000

Data Index: 986481 (C4 (Web Text))

Max Activating Token Index: 828