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

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

Neuron 1090 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: 0.0794. Min Range: -0.0794

Max Act: 0.0686. Min Act: -0.0002

Data Index: 16021 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1278008 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0002

Data Index: 533164 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0723. Min Act: -0.0002

Data Index: 364599 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0690. Min Act: -0.0002

Data Index: 440017 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0702. Min Act: -0.0002

Data Index: 287375 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0637. Min Act: -0.0002

Data Index: 162404 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0685. Min Act: -0.0002

Data Index: 738538 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0647. Min Act: -0.0002

Data Index: 472395 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0654. Min Act: -0.0002

Data Index: 61118 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0698. Min Act: -0.0002

Data Index: 844207 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0681. Min Act: -0.0002

Data Index: 482413 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0609. Min Act: -0.0002

Data Index: 645316 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0624. Min Act: -0.0002

Data Index: 141594 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0748. Min Act: -0.0002

Data Index: 459074 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1187517 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1304462 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0565. Min Act: -0.0002

Data Index: 686955 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0559. Min Act: -0.0002

Data Index: 882149 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0609. Min Act: -0.0002

Data Index: 215835 (C4 (Web Text))

Max Activating Token Index: 130