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

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

Neuron 1074 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: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0005

Data Index: 383767 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0005

Data Index: 64454 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0878. Min Act: -0.0005

Data Index: 940047 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0795. Min Act: -0.0005

Data Index: 66219 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0800. Min Act: -0.0005

Data Index: 1016 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0827. Min Act: -0.0005

Data Index: 1004908 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0796. Min Act: -0.0005

Data Index: 1305520 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0774. Min Act: -0.0005

Data Index: 991364 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0788. Min Act: -0.0005

Data Index: 417988 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0779. Min Act: -0.0005

Data Index: 1284641 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0756. Min Act: -0.0005

Data Index: 1284609 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0735. Min Act: -0.0005

Data Index: 26545 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0731. Min Act: -0.0005

Data Index: 309198 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0729. Min Act: -0.0005

Data Index: 499745 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0743. Min Act: -0.0005

Data Index: 13332 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0747. Min Act: -0.0005

Data Index: 782156 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0729. Min Act: -0.0005

Data Index: 1190809 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0727. Min Act: -0.0005

Data Index: 280033 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0708. Min Act: -0.0005

Data Index: 726563 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0734. Min Act: -0.0005

Data Index: 545415 (C4 (Web Text))

Max Activating Token Index: 118