Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2084 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0002

Data Index: 863864 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1078846 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0773. Min Act: -0.0002

Data Index: 846351 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0759. Min Act: -0.0003

Data Index: 389934 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0735. Min Act: -0.0002

Data Index: 558205 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0742. Min Act: -0.0002

Data Index: 337605 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0717. Min Act: -0.0002

Data Index: 836786 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0725. Min Act: -0.0003

Data Index: 630701 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0717. Min Act: -0.0002

Data Index: 581130 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0699. Min Act: -0.0002

Data Index: 567454 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0691. Min Act: -0.0002

Data Index: 380580 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1225333 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0689. Min Act: -0.0002

Data Index: 897289 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0681. Min Act: -0.0002

Data Index: 871540 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0692. Min Act: -0.0002

Data Index: 758545 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0693. Min Act: -0.0002

Data Index: 849791 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0688. Min Act: -0.0002

Data Index: 397210 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0696. Min Act: -0.0002

Data Index: 344193 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0671. Min Act: -0.0002

Data Index: 379509 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0682. Min Act: -0.0002

Data Index: 532496 (C4 (Web Text))

Max Activating Token Index: 252