Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1936 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0006

Data Index: 1058070 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0721. Min Act: -0.0006

Data Index: 517301 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0716. Min Act: -0.0006

Data Index: 911314 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0708. Min Act: -0.0006

Data Index: 995261 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0673. Min Act: -0.0006

Data Index: 690125 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0686. Min Act: -0.0006

Data Index: 937785 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0666. Min Act: -0.0006

Data Index: 109914 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0655. Min Act: -0.0006

Data Index: 1053725 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0628. Min Act: -0.0006

Data Index: 663825 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0651. Min Act: -0.0006

Data Index: 1339341 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0648. Min Act: -0.0006

Data Index: 1291211 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0643. Min Act: -0.0006

Data Index: 1108072 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0641. Min Act: -0.0006

Data Index: 638306 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0666. Min Act: -0.0006

Data Index: 872992 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0638. Min Act: -0.0006

Data Index: 175357 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0611. Min Act: -0.0006

Data Index: 1099240 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0600. Min Act: -0.0006

Data Index: 722958 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0590. Min Act: -0.0006

Data Index: 37599 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0594. Min Act: -0.0006

Data Index: 632517 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0600. Min Act: -0.0006

Data Index: 780438 (C4 (Web Text))

Max Activating Token Index: 630