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

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

Neuron 1087 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7848. Min Act: -0.0000

Data Index: 970847 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1048269 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8549. Min Act: -0.0000

Data Index: 670420 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8021. Min Act: -0.0000

Data Index: 20781 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8819. Min Act: -0.0000

Data Index: 218853 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8137. Min Act: -0.0000

Data Index: 683140 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7742. Min Act: -0.0000

Data Index: 345084 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8219. Min Act: -0.0000

Data Index: 246921 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8941. Min Act: -0.0000

Data Index: 687645 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8148. Min Act: -0.0000

Data Index: 804426 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7641. Min Act: -0.0000

Data Index: 86882 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7754. Min Act: -0.0000

Data Index: 438602 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1333964 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7528. Min Act: -0.0000

Data Index: 778461 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7089. Min Act: -0.0000

Data Index: 982693 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7142. Min Act: -0.0000

Data Index: 130961 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1272802 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.6961. Min Act: -0.0000

Data Index: 729247 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7092. Min Act: -0.0000

Data Index: 479218 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7044. Min Act: -0.0000

Data Index: 149817 (C4 (Web Text))

Max Activating Token Index: 411