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

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

Neuron 5029 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.4116. Min Act: -0.0001

Data Index: 1149432 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3846. Min Act: -0.0001

Data Index: 788383 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.4078. Min Act: -0.0001

Data Index: 733625 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3962. Min Act: -0.0001

Data Index: 411752 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.4031. Min Act: -0.0001

Data Index: 299500 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.4014. Min Act: -0.0001

Data Index: 185487 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3703. Min Act: -0.0001

Data Index: 386295 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1000760 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.4021. Min Act: -0.0001

Data Index: 939840 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3822. Min Act: -0.0001

Data Index: 484876 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3890. Min Act: -0.0001

Data Index: 840853 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3503. Min Act: -0.0001

Data Index: 946504 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3768. Min Act: -0.0001

Data Index: 475977 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3837. Min Act: -0.0001

Data Index: 465563 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3791. Min Act: -0.0001

Data Index: 215136 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3596. Min Act: -0.0001

Data Index: 587190 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3675. Min Act: -0.0001

Data Index: 1114358 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3772. Min Act: -0.0001

Data Index: 185615 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3632. Min Act: -0.0001

Data Index: 1009096 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3870. Min Act: -0.0001

Data Index: 1225910 (C4 (Web Text))

Max Activating Token Index: 44