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

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

Neuron 3730 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.9720. Min Act: -0.0001

Data Index: 1413425 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.9661. Min Act: -0.0001

Data Index: 1463333 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8124. Min Act: -0.0001

Data Index: 986424 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8479. Min Act: -0.0001

Data Index: 1092002 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8201. Min Act: -0.0001

Data Index: 20745 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7627. Min Act: -0.0001

Data Index: 198859 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7176. Min Act: -0.0001

Data Index: 65311 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7799. Min Act: -0.0001

Data Index: 141173 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7707. Min Act: -0.0001

Data Index: 545482 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7368. Min Act: -0.0001

Data Index: 956558 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7944. Min Act: -0.0001

Data Index: 653967 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6875. Min Act: -0.0001

Data Index: 537811 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7719. Min Act: -0.0001

Data Index: 429714 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7795. Min Act: -0.0001

Data Index: 401375 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1463529 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7084. Min Act: -0.0001

Data Index: 1302153 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1223891 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6743. Min Act: -0.0001

Data Index: 124177 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7330. Min Act: -0.0001

Data Index: 1378987 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7467. Min Act: -0.0001

Data Index: 42141 (C4 (Web Text))

Max Activating Token Index: 18