Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3325 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.8057. Min Act: -0.0000

Data Index: 559642 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.7871. Min Act: -0.0000

Data Index: 26007 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6847. Min Act: -0.0000

Data Index: 57659 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1093371 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.7728. Min Act: -0.0000

Data Index: 392802 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6632. Min Act: -0.0000

Data Index: 734546 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6699. Min Act: -0.0000

Data Index: 19173 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.7135. Min Act: -0.0000

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1029984 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1029839 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6645. Min Act: -0.0000

Data Index: 591472 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6561. Min Act: -0.0000

Data Index: 397720 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6076. Min Act: -0.0000

Data Index: 893641 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6236. Min Act: -0.0000

Data Index: 177106 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1164752 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6178. Min Act: -0.0000

Data Index: 628865 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6006. Min Act: -0.0000

Data Index: 642999 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6144. Min Act: -0.0000

Data Index: 143019 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5981. Min Act: -0.0000

Data Index: 164015 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5950. Min Act: -0.0000

Data Index: 734631 (C4 (Web Text))

Max Activating Token Index: 961