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

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

Neuron 80 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.7687. Min Act: -0.0000

Data Index: 1005916 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.3242. Min Act: -0.0000

Data Index: 975587 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.2366. Min Act: -0.0000

Data Index: 1123909 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.2172. Min Act: -0.0000

Data Index: 407990 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.2158. Min Act: -0.0000

Data Index: 777862 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.1546. Min Act: -0.0000

Data Index: 4309 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1255929 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0774. Min Act: -0.0000

Data Index: 90523 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0784. Min Act: 0.0001

Data Index: 369730 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0602. Min Act: 0.0000

Data Index: 690494 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.1146. Min Act: -0.0000

Data Index: 258639 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0536. Min Act: -0.0000

Data Index: 399041 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0380. Min Act: -0.0000

Data Index: 626807 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.1030. Min Act: -0.0000

Data Index: 73203 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.1067. Min Act: -0.0000

Data Index: 243735 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1095363 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 1.7687. Min Range: -1.7687

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1088449 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1293425 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 1.7687. Min Range: -1.7687

Max Act: 1.0383. Min Act: -0.0000

Data Index: 981149 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.7687. Min Range: -1.7687

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1016884 (C4 (Web Text))

Max Activating Token Index: 490