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

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

Neuron 5049 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: 0.2883. Min Range: -0.2883

Max Act: 0.2883. Min Act: -0.0001

Data Index: 1311216 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2829. Min Act: -0.0000

Data Index: 313463 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2565. Min Act: -0.0000

Data Index: 171 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2396. Min Act: -0.0001

Data Index: 912679 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1242121 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2060. Min Act: -0.0000

Data Index: 337759 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2054. Min Act: -0.0000

Data Index: 239946 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2113. Min Act: -0.0001

Data Index: 732347 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1192094 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1861. Min Act: -0.0000

Data Index: 973561 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1037140 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1007442 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1903. Min Act: -0.0000

Data Index: 453258 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1910. Min Act: -0.0000

Data Index: 152932 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1845. Min Act: -0.0000

Data Index: 798612 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1910. Min Act: -0.0001

Data Index: 693090 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1864. Min Act: -0.0000

Data Index: 666766 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1717. Min Act: -0.0000

Data Index: 745177 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1810. Min Act: -0.0000

Data Index: 860983 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1096114 (C4 (Web Text))

Max Activating Token Index: 904