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

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

Neuron 1803 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.1019. Min Act: -0.0002

Data Index: 824197 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1378042 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0895. Min Act: -0.0002

Data Index: 70675 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0851. Min Act: -0.0002

Data Index: 59587 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0824. Min Act: -0.0001

Data Index: 288573 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1186574 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0831. Min Act: -0.0002

Data Index: 337061 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1287766 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0797. Min Act: -0.0002

Data Index: 379507 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0816. Min Act: -0.0002

Data Index: 908535 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1294018 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0794. Min Act: -0.0002

Data Index: 874220 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0752. Min Act: -0.0002

Data Index: 57064 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0800. Min Act: -0.0002

Data Index: 726693 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1319730 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1171700 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0734. Min Act: -0.0002

Data Index: 603694 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1088334 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0762. Min Act: -0.0002

Data Index: 76042 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1536057 (Python Code)

Max Activating Token Index: 268