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

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

Neuron 502 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: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0002

Data Index: 567632 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0813. Min Act: -0.0002

Data Index: 56589 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0815. Min Act: -0.0002

Data Index: 323104 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0782. Min Act: -0.0002

Data Index: 114569 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0792. Min Act: -0.0002

Data Index: 214440 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0739. Min Act: -0.0002

Data Index: 601544 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1192903 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0739. Min Act: -0.0002

Data Index: 78224 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1001502 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0718. Min Act: -0.0002

Data Index: 481034 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1331382 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0718. Min Act: -0.0002

Data Index: 900023 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0701. Min Act: -0.0002

Data Index: 487654 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0696. Min Act: -0.0001

Data Index: 266197 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0707. Min Act: -0.0002

Data Index: 502831 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0701. Min Act: -0.0002

Data Index: 857699 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0713. Min Act: -0.0002

Data Index: 905258 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1249625 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0722. Min Act: -0.0002

Data Index: 77882 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0665. Min Act: -0.0001

Data Index: 612560 (C4 (Web Text))

Max Activating Token Index: 964