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

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

Neuron 544 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4880. Min Act: -0.0000

Data Index: 466417 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4777. Min Act: -0.0000

Data Index: 940859 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4495. Min Act: -0.0000

Data Index: 661782 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4227. Min Act: -0.0000

Data Index: 857974 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3767. Min Act: -0.0000

Data Index: 427748 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4421. Min Act: -0.0000

Data Index: 531760 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3886. Min Act: -0.0000

Data Index: 107902 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1355445 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4096. Min Act: -0.0000

Data Index: 272542 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1359075 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3491. Min Act: -0.0000

Data Index: 859891 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3545. Min Act: -0.0000

Data Index: 225704 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3736. Min Act: -0.0000

Data Index: 791901 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3269. Min Act: -0.0000

Data Index: 837661 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3566. Min Act: -0.0000

Data Index: 447469 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3507. Min Act: -0.0000

Data Index: 497780 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3341. Min Act: -0.0000

Data Index: 371955 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3291. Min Act: -0.0000

Data Index: 906687 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3035. Min Act: -0.0000

Data Index: 732631 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1183949 (C4 (Web Text))

Max Activating Token Index: 867