Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 725 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.8335. Min Act: -0.0004

Data Index: 110904 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.8252. Min Act: -0.0004

Data Index: 615273 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7491. Min Act: -0.0004

Data Index: 319607 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7703. Min Act: -0.0004

Data Index: 521792 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.8722. Min Act: -0.0004

Data Index: 729205 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7641. Min Act: -0.0004

Data Index: 679818 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7166. Min Act: -0.0004

Data Index: 1288581 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7620. Min Act: -0.0004

Data Index: 963526 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7360. Min Act: -0.0004

Data Index: 851476 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6460. Min Act: -0.0004

Data Index: 470981 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7044. Min Act: -0.0004

Data Index: 602905 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6375. Min Act: -0.0004

Data Index: 1315094 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7185. Min Act: -0.0004

Data Index: 1280517 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6925. Min Act: -0.0004

Data Index: 400149 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.8060. Min Act: -0.0004

Data Index: 540936 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7030. Min Act: -0.0004

Data Index: 1023838 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6684. Min Act: -0.0004

Data Index: 173130 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6866. Min Act: -0.0004

Data Index: 1307974 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7322. Min Act: -0.0004

Data Index: 576358 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6634. Min Act: -0.0004

Data Index: 1233220 (C4 (Web Text))

Max Activating Token Index: 876