Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1877 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.7963. Min Act: -0.0000

Data Index: 271880 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.7252. Min Act: -0.0000

Data Index: 465998 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6634. Min Act: -0.0000

Data Index: 503570 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1315585 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.7351. Min Act: -0.0000

Data Index: 468053 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6788. Min Act: -0.0000

Data Index: 314662 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6333. Min Act: -0.0001

Data Index: 766253 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1107527 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6430. Min Act: -0.0000

Data Index: 674442 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6595. Min Act: -0.0000

Data Index: 883772 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6097. Min Act: -0.0001

Data Index: 930211 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1054625 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6040. Min Act: -0.0000

Data Index: 457249 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1107430 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.5855. Min Act: -0.0001

Data Index: 826003 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6061. Min Act: -0.0000

Data Index: 12170 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1009679 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1176527 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.5979. Min Act: -0.0000

Data Index: 257619 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.7963. Min Range: -0.7963

Max Act: 0.6284. Min Act: -0.0000

Data Index: 10073 (C4 (Web Text))

Max Activating Token Index: 728