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

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

Neuron 4798 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.9733. Min Act: -0.0002

Data Index: 825672 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.9984. Min Act: -0.0002

Data Index: 1102892 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.9149. Min Act: -0.0003

Data Index: 1214827 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.9061. Min Act: -0.0002

Data Index: 580693 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.8565. Min Act: -0.0002

Data Index: 602009 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.8249. Min Act: -0.0003

Data Index: 625491 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.8022. Min Act: -0.0003

Data Index: 976023 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.8454. Min Act: -0.0002

Data Index: 218732 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7906. Min Act: -0.0002

Data Index: 1299659 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7804. Min Act: -0.0002

Data Index: 602439 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.8245. Min Act: -0.0002

Data Index: 904560 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7983. Min Act: -0.0003

Data Index: 565014 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7230. Min Act: -0.0002

Data Index: 483758 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7452. Min Act: -0.0003

Data Index: 547395 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7042. Min Act: -0.0003

Data Index: 564495 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7245. Min Act: -0.0003

Data Index: 1065797 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7154. Min Act: -0.0002

Data Index: 300183 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6893. Min Act: -0.0003

Data Index: 859523 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6754. Min Act: -0.0003

Data Index: 672132 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6737. Min Act: -0.0002

Data Index: 1267138 (C4 (Web Text))

Max Activating Token Index: 739