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

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

Neuron 4274 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1816. Min Act: -0.0000

Data Index: 77764 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1796. Min Act: -0.0000

Data Index: 693449 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1870. Min Act: -0.0000

Data Index: 576409 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1848. Min Act: -0.0000

Data Index: 351857 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1862. Min Act: -0.0000

Data Index: 430364 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1754. Min Act: -0.0000

Data Index: 699040 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1781. Min Act: -0.0000

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1626. Min Act: -0.0000

Data Index: 159194 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1687. Min Act: -0.0000

Data Index: 345969 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1296038 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1611. Min Act: -0.0000

Data Index: 74566 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1648. Min Act: -0.0000

Data Index: 439941 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1596. Min Act: -0.0000

Data Index: 784873 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1624. Min Act: -0.0000

Data Index: 783441 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1574. Min Act: -0.0000

Data Index: 450111 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1488. Min Act: -0.0000

Data Index: 608405 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1134865 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1466. Min Act: -0.0000

Data Index: 646269 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1432. Min Act: -0.0000

Data Index: 495591 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1237292 (C4 (Web Text))

Max Activating Token Index: 98