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

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

Neuron 968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0906. Min Act: -0.0005

Data Index: 761747 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0903. Min Act: -0.0005

Data Index: 142602 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0846. Min Act: -0.0005

Data Index: 1330038 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0824. Min Act: -0.0005

Data Index: 1185958 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0812. Min Act: -0.0005

Data Index: 525005 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0755. Min Act: -0.0005

Data Index: 632116 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0758. Min Act: -0.0005

Data Index: 205045 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0724. Min Act: -0.0005

Data Index: 851446 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0736. Min Act: -0.0005

Data Index: 66094 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0722. Min Act: -0.0005

Data Index: 886090 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0733. Min Act: -0.0005

Data Index: 705932 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0749. Min Act: -0.0005

Data Index: 19079 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0718. Min Act: -0.0005

Data Index: 1178346 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0726. Min Act: -0.0005

Data Index: 170260 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0727. Min Act: -0.0005

Data Index: 530760 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0690. Min Act: -0.0005

Data Index: 19379 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0711. Min Act: -0.0005

Data Index: 718043 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0683. Min Act: -0.0005

Data Index: 935870 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0705. Min Act: -0.0005

Data Index: 679951 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0748. Min Act: -0.0005

Data Index: 573863 (C4 (Web Text))

Max Activating Token Index: 836