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

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

Neuron 4627 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.6259. Min Act: -0.0000

Data Index: 48853 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3824. Min Act: -0.0000

Data Index: 782854 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1298367 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1075316 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5343. Min Act: -0.0000

Data Index: 559881 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1264464 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5067. Min Act: -0.0000

Data Index: 680585 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4856. Min Act: -0.0000

Data Index: 352685 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4828. Min Act: -0.0000

Data Index: 147920 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4880. Min Act: -0.0000

Data Index: 360105 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4901. Min Act: -0.0000

Data Index: 848855 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4874. Min Act: -0.0000

Data Index: 685438 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5029. Min Act: -0.0000

Data Index: 583966 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4901. Min Act: -0.0000

Data Index: 353294 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4669. Min Act: -0.0000

Data Index: 234878 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4771. Min Act: -0.0000

Data Index: 481341 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4598. Min Act: -0.0000

Data Index: 792848 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1039097 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4313. Min Act: -0.0000

Data Index: 589616 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1345678 (C4 (Web Text))

Max Activating Token Index: 477