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

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

Neuron 1548 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1255. Min Act: -0.0001

Data Index: 465173 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1501. Min Act: -0.0001

Data Index: 747479 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1432. Min Act: -0.0001

Data Index: 786162 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1183603 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1291907 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1023755 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1024489 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1010. Min Act: -0.0001

Data Index: 363500 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1335297 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1287273 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1217906 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0891. Min Act: -0.0000

Data Index: 789921 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0834. Min Act: -0.0001

Data Index: 866130 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0850. Min Act: -0.0000

Data Index: 198781 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0862. Min Act: -0.0001

Data Index: 148220 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0805. Min Act: -0.0000

Data Index: 64003 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0808. Min Act: -0.0000

Data Index: 655766 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0824. Min Act: -0.0000

Data Index: 194912 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0783. Min Act: -0.0000

Data Index: 593930 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0792. Min Act: -0.0000

Data Index: 92152 (C4 (Web Text))

Max Activating Token Index: 211