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

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

Neuron 1391 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: 1.1754. Min Range: -1.1754

Max Act: 1.0340. Min Act: -0.0002

Data Index: 1029421 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1015. Min Act: -0.0002

Data Index: 1003167 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9819. Min Act: -0.0002

Data Index: 1148916 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.0609. Min Act: -0.0002

Data Index: 472478 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1529. Min Act: -0.0002

Data Index: 1060923 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1754. Min Act: -0.0002

Data Index: 1341620 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1525. Min Act: -0.0002

Data Index: 178700 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1729. Min Act: -0.0002

Data Index: 852994 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9089. Min Act: -0.0002

Data Index: 183486 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9428. Min Act: -0.0002

Data Index: 375441 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9646. Min Act: -0.0002

Data Index: 279894 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7884. Min Act: -0.0002

Data Index: 72469 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9768. Min Act: -0.0002

Data Index: 609507 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9972. Min Act: -0.0002

Data Index: 894954 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9155. Min Act: -0.0002

Data Index: 193561 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1065. Min Act: -0.0002

Data Index: 246219 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9454. Min Act: -0.0002

Data Index: 1356774 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.0277. Min Act: -0.0002

Data Index: 792160 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.6608. Min Act: -0.0002

Data Index: 575451 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.0235. Min Act: -0.0002

Data Index: 893815 (C4 (Web Text))

Max Activating Token Index: 941