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

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

Neuron 4319 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: 0.9839. Min Range: -0.9839

Max Act: 0.9839. Min Act: -0.0001

Data Index: 737986 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.9427. Min Act: -0.0001

Data Index: 925364 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.8174. Min Act: -0.0001

Data Index: 231856 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.8254. Min Act: -0.0001

Data Index: 2900 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.9029. Min Act: -0.0001

Data Index: 861575 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.7469. Min Act: -0.0001

Data Index: 1333271 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.8944. Min Act: -0.0001

Data Index: 961783 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.7834. Min Act: -0.0001

Data Index: 721919 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.7555. Min Act: -0.0001

Data Index: 141169 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.7363. Min Act: -0.0001

Data Index: 531039 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.7135. Min Act: -0.0001

Data Index: 903256 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.8261. Min Act: -0.0001

Data Index: 893199 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.7941. Min Act: -0.0001

Data Index: 873552 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.7808. Min Act: -0.0001

Data Index: 756668 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.8952. Min Act: -0.0001

Data Index: 932610 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.6563. Min Act: -0.0001

Data Index: 684385 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.8892. Min Act: -0.0001

Data Index: 197353 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.6905. Min Act: -0.0001

Data Index: 562436 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.9220. Min Act: -0.0001

Data Index: 706440 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.9839. Min Range: -0.9839

Max Act: 0.6313. Min Act: -0.0001

Data Index: 753961 (C4 (Web Text))

Max Activating Token Index: 340