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

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

Neuron 2222 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0025. Min Range: -1.0025

Max Act: 1.0025. Min Act: -0.0000

Data Index: 282687 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9804. Min Act: -0.0000

Data Index: 612274 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9420. Min Act: -0.0000

Data Index: 753715 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1535874 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1108237 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8314. Min Act: -0.0000

Data Index: 630884 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1065455 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1136320 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1463313 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6995. Min Act: -0.0000

Data Index: 379446 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6712. Min Act: -0.0000

Data Index: 403794 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1621760 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6906. Min Act: -0.0000

Data Index: 230552 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1574763 (Python Code)

Max Activating Token Index: 453

Text #14

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1182395 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1506060 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6383. Min Act: -0.0000

Data Index: 114242 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.5991. Min Act: -0.0000

Data Index: 75980 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1549742 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.6331. Min Act: -0.0000

Data Index: 7971 (C4 (Web Text))

Max Activating Token Index: 1011