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

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

Neuron 2049 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: 0.1321. Min Range: -0.1321

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1530587 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1514806 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1440492 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1506534 (Python Code)

Max Activating Token Index: 207

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1049. Min Act: -0.0000

Data Index: 978676 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1645021 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1060201 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1628402 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0989. Min Act: -0.0000

Data Index: 505681 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1509508 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1580368 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1004. Min Act: 0.0000

Data Index: 851291 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1166718 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1554443 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0867. Min Act: -0.0000

Data Index: 283172 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0882. Min Act: -0.0000

Data Index: 597673 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0777. Min Act: -0.0000

Data Index: 538948 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1196489 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0784. Min Act: -0.0000

Data Index: 422633 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1066506 (C4 (Web Text))

Max Activating Token Index: 133