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

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

Neuron 2744 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: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0001

Data Index: 70234 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0792. Min Act: -0.0001

Data Index: 497230 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0720. Min Act: -0.0001

Data Index: 339643 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0725. Min Act: -0.0001

Data Index: 90663 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0764. Min Act: -0.0001

Data Index: 687178 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0697. Min Act: -0.0001

Data Index: 105663 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0680. Min Act: -0.0001

Data Index: 714956 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0654. Min Act: -0.0001

Data Index: 908597 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0657. Min Act: -0.0001

Data Index: 183316 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1220945 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0639. Min Act: -0.0001

Data Index: 462039 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0619. Min Act: -0.0001

Data Index: 392628 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0616. Min Act: -0.0001

Data Index: 153864 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1385780 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0636. Min Act: -0.0001

Data Index: 272444 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1232761 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1016523 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0579. Min Act: -0.0001

Data Index: 978745 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0646. Min Act: -0.0001

Data Index: 7429 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0600. Min Act: -0.0001

Data Index: 984391 (C4 (Web Text))

Max Activating Token Index: 972