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

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

Neuron 1456 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.4853. Min Act: -0.0001

Data Index: 339884 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.7908. Min Act: -0.0001

Data Index: 82080 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.7265. Min Act: -0.0001

Data Index: 863688 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.2679. Min Act: -0.0001

Data Index: 1149745 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.5437. Min Act: -0.0001

Data Index: 496707 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.4260. Min Act: -0.0001

Data Index: 284393 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.4780. Min Act: -0.0001

Data Index: 791476 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.3087. Min Act: -0.0001

Data Index: 337973 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.2689. Min Act: -0.0001

Data Index: 1056153 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.2543. Min Act: -0.0001

Data Index: 772717 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1136. Min Act: -0.0001

Data Index: 70823 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1273. Min Act: -0.0001

Data Index: 596037 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1555. Min Act: -0.0001

Data Index: 726155 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1823. Min Act: -0.0001

Data Index: 1314837 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1582. Min Act: -0.0001

Data Index: 842435 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1734. Min Act: -0.0001

Data Index: 248104 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1093. Min Act: -0.0001

Data Index: 605815 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.3108. Min Act: -0.0001

Data Index: 178279 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0613. Min Act: -0.0001

Data Index: 517543 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1419. Min Act: -0.0001

Data Index: 503180 (C4 (Web Text))

Max Activating Token Index: 107