Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 614 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1382997 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 861

Text #2

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1612346 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1580462 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0003

Data Index: 949082 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0003

Data Index: 1167119 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0003

Data Index: 183905 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 1338166 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0003

Data Index: 462520 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 19845 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 434751 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 984260 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 831586 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0002

Data Index: 437298 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 309875 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 1014009 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 337106 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1411172 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 24307 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0003

Data Index: 438579 (C4 (Web Text))

Max Activating Token Index: 404