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

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

Neuron 2671 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1089374 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0863. Min Act: -0.0002

Data Index: 796623 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1047944 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0818. Min Act: -0.0002

Data Index: 684405 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0812. Min Act: -0.0003

Data Index: 242918 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0833. Min Act: -0.0002

Data Index: 395404 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0806. Min Act: -0.0002

Data Index: 557997 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0761. Min Act: -0.0002

Data Index: 59196 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0810. Min Act: -0.0002

Data Index: 162453 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1230969 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0775. Min Act: -0.0002

Data Index: 679241 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0758. Min Act: -0.0002

Data Index: 779339 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0756. Min Act: -0.0002

Data Index: 619044 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1001228 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0746. Min Act: -0.0003

Data Index: 593745 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0750. Min Act: -0.0002

Data Index: 472500 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0747. Min Act: -0.0002

Data Index: 33965 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0708. Min Act: -0.0003

Data Index: 244139 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1045677 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0761. Min Act: -0.0002

Data Index: 537811 (C4 (Web Text))

Max Activating Token Index: 764