Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 712 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0002

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0918. Min Act: -0.0003

Data Index: 132628 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0916. Min Act: -0.0003

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1040733 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0914. Min Act: -0.0003

Data Index: 858356 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0875. Min Act: -0.0003

Data Index: 1274786 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0812. Min Act: -0.0002

Data Index: 430303 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0872. Min Act: -0.0003

Data Index: 1216904 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0849. Min Act: -0.0002

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0850. Min Act: -0.0002

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0791. Min Act: -0.0002

Data Index: 299618 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0760. Min Act: -0.0002

Data Index: 487922 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0760. Min Act: -0.0003

Data Index: 196487 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1248859 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0809. Min Act: -0.0002

Data Index: 988570 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0748. Min Act: -0.0002

Data Index: 452373 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0770. Min Act: -0.0002

Data Index: 10055 (C4 (Web Text))

Max Activating Token Index: 217