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

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

Neuron 1564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4504. Min Range: -5.4504

Max Act: 5.4504. Min Act: -0.0001

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 5.4504. Min Range: -5.4504

Max Act: 4.1565. Min Act: -0.0001

Data Index: 1336566 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 5.4504. Min Range: -5.4504

Max Act: 3.4116. Min Act: -0.0001

Data Index: 1383 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 5.4504. Min Range: -5.4504

Max Act: 3.5889. Min Act: -0.0001

Data Index: 198433 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 5.4504. Min Range: -5.4504

Max Act: 3.2478. Min Act: -0.0001

Data Index: 885303 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 5.4504. Min Range: -5.4504

Max Act: 3.3687. Min Act: -0.0001

Data Index: 1118649 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 5.4504. Min Range: -5.4504

Max Act: 3.3177. Min Act: -0.0001

Data Index: 921356 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.4504. Min Range: -5.4504

Max Act: 3.0794. Min Act: -0.0001

Data Index: 27083 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 5.4504. Min Range: -5.4504

Max Act: 3.2001. Min Act: -0.0001

Data Index: 1193722 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.9391. Min Act: -0.0001

Data Index: 1119384 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.7496. Min Act: -0.0001

Data Index: 163623 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.9026. Min Act: -0.0001

Data Index: 156094 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.7224. Min Act: -0.0001

Data Index: 829809 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.8055. Min Act: -0.0001

Data Index: 749855 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.7959. Min Act: -0.0001

Data Index: 642316 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.7948. Min Act: -0.0001

Data Index: 693359 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.7490. Min Act: -0.0001

Data Index: 134672 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.8728. Min Act: -0.0001

Data Index: 843222 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.7124. Min Act: -0.0001

Data Index: 260 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 5.4504. Min Range: -5.4504

Max Act: 2.6271. Min Act: -0.0001

Data Index: 268827 (C4 (Web Text))

Max Activating Token Index: 963