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

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

Neuron 1459 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: 3.2195. Min Range: -3.2195

Max Act: 3.2009. Min Act: -0.0000

Data Index: 406657 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 3.2195. Min Range: -3.2195

Max Act: 3.2195. Min Act: -0.0000

Data Index: 26974 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 3.2195. Min Range: -3.2195

Max Act: 3.1618. Min Act: -0.0000

Data Index: 665047 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.9833. Min Act: -0.0000

Data Index: 854815 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.9271. Min Act: -0.0000

Data Index: 281281 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.6503. Min Act: -0.0000

Data Index: 92439 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.6001. Min Act: -0.0000

Data Index: 1159449 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.6782. Min Act: -0.0000

Data Index: 217171 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5711. Min Act: -0.0000

Data Index: 733265 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5711. Min Act: -0.0000

Data Index: 1157978 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5692. Min Act: -0.0000

Data Index: 192877 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5549. Min Act: -0.0000

Data Index: 123772 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.6082. Min Act: -0.0000

Data Index: 804895 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5551. Min Act: -0.0000

Data Index: 297156 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.2860. Min Act: -0.0000

Data Index: 1317359 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5240. Min Act: -0.0000

Data Index: 75304 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5143. Min Act: -0.0000

Data Index: 1267583 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.5332. Min Act: -0.0000

Data Index: 729993 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.4925. Min Act: -0.0000

Data Index: 1151242 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.2195. Min Range: -3.2195

Max Act: 2.4459. Min Act: -0.0000

Data Index: 209448 (C4 (Web Text))

Max Activating Token Index: 282