Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 853 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2204. Min Act: -0.0001

Data Index: 513903 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2074. Min Act: -0.0002

Data Index: 613159 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1054672 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2067. Min Act: -0.0002

Data Index: 138636 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1807. Min Act: -0.0002

Data Index: 909938 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1908. Min Act: -0.0001

Data Index: 482443 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2072. Min Act: -0.0001

Data Index: 547444 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1730. Min Act: -0.0002

Data Index: 85939 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1812. Min Act: -0.0002

Data Index: 109239 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1856. Min Act: -0.0001

Data Index: 819230 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1090130 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1770. Min Act: -0.0002

Data Index: 246357 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1818. Min Act: -0.0002

Data Index: 588690 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1788. Min Act: -0.0002

Data Index: 1215262 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1721. Min Act: -0.0002

Data Index: 1051861 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1732. Min Act: -0.0002

Data Index: 571166 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1188560 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1721. Min Act: -0.0002

Data Index: 429182 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1784. Min Act: -0.0002

Data Index: 531059 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1748. Min Act: -0.0001

Data Index: 570654 (C4 (Web Text))

Max Activating Token Index: 791