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

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

Neuron 155 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0001

Data Index: 999945 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0891. Min Act: -0.0001

Data Index: 423006 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0761. Min Act: -0.0001

Data Index: 359893 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1351731 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0768. Min Act: -0.0001

Data Index: 643489 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0708. Min Act: -0.0001

Data Index: 677297 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0668. Min Act: -0.0001

Data Index: 633311 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0690. Min Act: -0.0001

Data Index: 640944 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0728. Min Act: -0.0001

Data Index: 505926 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0692. Min Act: -0.0001

Data Index: 6020 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0682. Min Act: -0.0001

Data Index: 499264 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0718. Min Act: -0.0001

Data Index: 737596 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0731. Min Act: -0.0000

Data Index: 550489 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0774. Min Act: -0.0001

Data Index: 830117 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0671. Min Act: -0.0001

Data Index: 633903 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0675. Min Act: -0.0001

Data Index: 194679 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0696. Min Act: -0.0001

Data Index: 451553 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0712. Min Act: -0.0001

Data Index: 756560 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1309491 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0625. Min Act: -0.0001

Data Index: 143911 (C4 (Web Text))

Max Activating Token Index: 585