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

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

Neuron 4848 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6751. Min Act: -0.0002

Data Index: 276909 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6357. Min Act: -0.0002

Data Index: 654132 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6298. Min Act: -0.0002

Data Index: 792302 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6018. Min Act: -0.0002

Data Index: 1152970 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5917. Min Act: -0.0002

Data Index: 1009049 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5728. Min Act: -0.0002

Data Index: 423407 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5430. Min Act: -0.0002

Data Index: 879873 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5758. Min Act: -0.0002

Data Index: 560909 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5519. Min Act: -0.0002

Data Index: 342489 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5536. Min Act: -0.0002

Data Index: 786050 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5151. Min Act: -0.0002

Data Index: 1167872 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4760. Min Act: -0.0002

Data Index: 996056 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5514. Min Act: -0.0002

Data Index: 462051 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5306. Min Act: -0.0002

Data Index: 575019 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5589. Min Act: -0.0002

Data Index: 212746 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4811. Min Act: -0.0002

Data Index: 577366 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5013. Min Act: -0.0002

Data Index: 1263226 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5586. Min Act: -0.0002

Data Index: 13815 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5435. Min Act: -0.0002

Data Index: 1281955 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5415. Min Act: -0.0002

Data Index: 222657 (C4 (Web Text))

Max Activating Token Index: 185