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

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

Neuron 18 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8819. Min Act: -0.0001

Data Index: 656009 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.8693. Min Act: -0.0001

Data Index: 667834 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6724. Min Act: -0.0001

Data Index: 904173 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.9284. Min Act: -0.0001

Data Index: 942822 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7519. Min Act: -0.0001

Data Index: 764016 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6546. Min Act: -0.0001

Data Index: 246734 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6902. Min Act: -0.0001

Data Index: 1250338 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.7758. Min Act: -0.0001

Data Index: 207563 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.5236. Min Act: -0.0000

Data Index: 510384 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6454. Min Act: -0.0001

Data Index: 1291009 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6211. Min Act: -0.0001

Data Index: 1296020 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6461. Min Act: -0.0001

Data Index: 981679 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6743. Min Act: -0.0001

Data Index: 463569 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.5789. Min Act: -0.0001

Data Index: 153436 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6374. Min Act: -0.0001

Data Index: 230198 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6114. Min Act: -0.0001

Data Index: 1202558 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6056. Min Act: -0.0001

Data Index: 1208746 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6352. Min Act: -0.0001

Data Index: 385557 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.5831. Min Act: -0.0001

Data Index: 539789 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.9284. Min Range: -0.9284

Max Act: 0.6102. Min Act: -0.0001

Data Index: 782933 (C4 (Web Text))

Max Activating Token Index: 535