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

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

Neuron 3917 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.3351. Min Act: -0.0000

Data Index: 1186916 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1416296 (Python Code)

Max Activating Token Index: 399

Text #2

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.2103. Min Act: -0.0000

Data Index: 475003 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.0688. Min Act: -0.0000

Data Index: 850794 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1583083 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1636532 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.0000. Min Act: -0.0000

Data Index: 712144 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9724. Min Act: -0.0000

Data Index: 331711 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9714. Min Act: -0.0000

Data Index: 122903 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1393352 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1621494 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9027. Min Act: -0.0000

Data Index: 714205 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1514154 (Python Code)

Max Activating Token Index: 461

Text #13

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1530381 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.8913. Min Act: -0.0000

Data Index: 587048 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9047. Min Act: -0.0000

Data Index: 463806 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1606075 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1624210 (Python Code)

Max Activating Token Index: 884

Text #18

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1420214 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1143113 (C4 (Web Text))

Max Activating Token Index: 1004