Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3037 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1410432 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1407501 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1500194 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0896. Min Act: -0.0001

Data Index: 394351 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1590091 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0762. Min Act: -0.0001

Data Index: 875717 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1357251 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0852. Min Act: -0.0001

Data Index: 971593 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1649904 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1475230 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1655064 (Python Code)

Max Activating Token Index: 1000

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1390794 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1521765 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1579481 (Python Code)

Max Activating Token Index: 261

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1535625 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0830. Min Act: -0.0001

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0795. Min Act: -0.0001

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0781. Min Act: -0.0001

Data Index: 265721 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1461468 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1481151 (Python Code)

Max Activating Token Index: 507