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

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

Neuron 2904 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1085828 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0896. Min Act: -0.0000

Data Index: 661334 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0883. Min Act: -0.0000

Data Index: 651185 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1040210 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0864. Min Act: -0.0000

Data Index: 79257 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0842. Min Act: -0.0000

Data Index: 863787 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0816. Min Act: -0.0000

Data Index: 354846 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0826. Min Act: -0.0000

Data Index: 198568 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0787. Min Act: -0.0000

Data Index: 735388 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1201588 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0807. Min Act: -0.0000

Data Index: 168810 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1613172 (Python Code)

Max Activating Token Index: 692

Text #12

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0755. Min Act: -0.0000

Data Index: 114608 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1247119 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0794. Min Act: -0.0000

Data Index: 866163 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1108960 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0762. Min Act: -0.0000

Data Index: 807934 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0751. Min Act: -0.0000

Data Index: 294972 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1348683 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0752. Min Act: -0.0000

Data Index: 875565 (C4 (Web Text))

Max Activating Token Index: 72