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

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

Neuron 4790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8700. Min Act: -0.0000

Data Index: 630038 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8556. Min Act: -0.0000

Data Index: 291903 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1115950 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1106045 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1224622 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7845. Min Act: -0.0000

Data Index: 959969 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7012. Min Act: -0.0000

Data Index: 459318 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7090. Min Act: -0.0000

Data Index: 706039 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1188505 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6675. Min Act: -0.0000

Data Index: 892853 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6334. Min Act: -0.0000

Data Index: 873011 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1084218 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5969. Min Act: -0.0000

Data Index: 627709 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5816. Min Act: -0.0000

Data Index: 892557 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5423. Min Act: -0.0000

Data Index: 533318 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6081. Min Act: -0.0000

Data Index: 626154 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1350639 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5197. Min Act: -0.0000

Data Index: 452628 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5255. Min Act: -0.0000

Data Index: 227792 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.4785. Min Act: -0.0000

Data Index: 161440 (C4 (Web Text))

Max Activating Token Index: 780