Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1340 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0016. Min Act: -0.0005

Data Index: 1494490 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0017. Min Act: -0.0005

Data Index: 1434735 (Python Code)

Max Activating Token Index: 379

Text #2

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0016. Min Act: -0.0005

Data Index: 903171 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1614149 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 396783 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1626275 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1462229 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1408219 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1465536 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 532770 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 337714 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1647188 (Python Code)

Max Activating Token Index: 359

Text #12

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1655835 (Python Code)

Max Activating Token Index: 465

Text #13

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0005

Data Index: 496129 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1392241 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1402746 (Python Code)

Max Activating Token Index: 272

Text #16

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1246705 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1114378 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1571323 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0005

Data Index: 1494037 (Python Code)

Max Activating Token Index: 462