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

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

Neuron 5274 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1609792 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1396731 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1513836 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1522068 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1458591 (Python Code)

Max Activating Token Index: 905

Text #5

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1561998 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4051. Min Act: -0.0000

Data Index: 784503 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4428. Min Act: -0.0000

Data Index: 697109 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1561554 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1391807 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3978. Min Act: -0.0000

Data Index: 848392 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1412906 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1458910 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1315218 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1434589 (Python Code)

Max Activating Token Index: 373

Text #15

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3759. Min Act: -0.0000

Data Index: 517888 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1632513 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1449624 (Python Code)

Max Activating Token Index: 579

Text #18

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1381711 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1520220 (Python Code)

Max Activating Token Index: 180