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

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

Neuron 2851 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: 1.1928. Min Range: -1.1928

Max Act: 1.1928. Min Act: -0.0000

Data Index: 535030 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.9375. Min Act: -0.0000

Data Index: 203395 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8281. Min Act: -0.0000

Data Index: 855818 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7695. Min Act: -0.0000

Data Index: 511811 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7513. Min Act: -0.0000

Data Index: 839317 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8127. Min Act: -0.0000

Data Index: 388033 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7846. Min Act: -0.0000

Data Index: 795256 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7177. Min Act: -0.0000

Data Index: 477177 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1122734 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.6991. Min Act: -0.0000

Data Index: 850453 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7405. Min Act: -0.0000

Data Index: 654947 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7348. Min Act: -0.0000

Data Index: 916602 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7284. Min Act: -0.0001

Data Index: 390023 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.6593. Min Act: -0.0000

Data Index: 40615 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7684. Min Act: -0.0000

Data Index: 741433 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1001458 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.6746. Min Act: -0.0000

Data Index: 157769 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.6937. Min Act: -0.0000

Data Index: 214593 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.6670. Min Act: -0.0001

Data Index: 319573 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7010. Min Act: -0.0000

Data Index: 443301 (C4 (Web Text))

Max Activating Token Index: 614