Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 850 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1215. Min Act: -0.0002

Data Index: 177256 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1051. Min Act: -0.0002

Data Index: 416309 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1251076 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0984. Min Act: -0.0002

Data Index: 620473 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0961. Min Act: -0.0002

Data Index: 763093 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0957. Min Act: -0.0001

Data Index: 593886 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0946. Min Act: -0.0002

Data Index: 67032 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0971. Min Act: -0.0002

Data Index: 208134 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0943. Min Act: -0.0002

Data Index: 589853 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0960. Min Act: -0.0002

Data Index: 583211 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0895. Min Act: -0.0002

Data Index: 395012 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0950. Min Act: -0.0002

Data Index: 303478 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0910. Min Act: -0.0002

Data Index: 978842 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0881. Min Act: -0.0002

Data Index: 275644 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0901. Min Act: -0.0002

Data Index: 519084 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0900. Min Act: -0.0002

Data Index: 539856 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1190418 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0883. Min Act: -0.0002

Data Index: 292770 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0886. Min Act: -0.0002

Data Index: 6700 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0911. Min Act: -0.0002

Data Index: 203930 (C4 (Web Text))

Max Activating Token Index: 319