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

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

Neuron 901 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.5971. Min Act: -0.0000

Data Index: 216185 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.4167. Min Act: -0.0000

Data Index: 777465 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.2892. Min Act: -0.0000

Data Index: 2916 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.3611. Min Act: -0.0000

Data Index: 885321 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.2778. Min Act: -0.0000

Data Index: 967168 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.2779. Min Act: -0.0000

Data Index: 743393 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.2204. Min Act: -0.0000

Data Index: 665312 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.2349. Min Act: -0.0000

Data Index: 7368 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1585. Min Act: -0.0000

Data Index: 677235 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1879. Min Act: -0.0000

Data Index: 228697 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1080500 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1608. Min Act: -0.0001

Data Index: 420370 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.0583. Min Act: -0.0000

Data Index: 163514 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1150. Min Act: -0.0001

Data Index: 595945 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1381. Min Act: -0.0000

Data Index: 974135 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.0910. Min Act: -0.0000

Data Index: 127789 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.0824. Min Act: -0.0000

Data Index: 890759 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1219. Min Act: -0.0000

Data Index: 326782 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1164350 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 1.5971. Min Range: -1.5971

Max Act: 1.1166. Min Act: -0.0000

Data Index: 317789 (C4 (Web Text))

Max Activating Token Index: 517