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

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

Neuron 671 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0900. Min Range: -1.0900

Max Act: 1.0900. Min Act: -0.0000

Data Index: 639024 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1134446 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.9102. Min Act: -0.0000

Data Index: 466633 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.7769. Min Act: 0.0000

Data Index: 562614 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.7043. Min Act: 0.0000

Data Index: 48004 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6693. Min Act: -0.0000

Data Index: 188843 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6889. Min Act: -0.0000

Data Index: 938806 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.7154. Min Act: -0.0000

Data Index: 359019 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6762. Min Act: -0.0000

Data Index: 843665 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6539. Min Act: -0.0000

Data Index: 338202 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6994. Min Act: 0.0001

Data Index: 791530 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6430. Min Act: 0.0000

Data Index: 1049198 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6434. Min Act: -0.0000

Data Index: 101856 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6580. Min Act: -0.0000

Data Index: 214457 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6148. Min Act: -0.0000

Data Index: 338133 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6722. Min Act: -0.0000

Data Index: 793873 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6473. Min Act: 0.0000

Data Index: 1207891 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6331. Min Act: -0.0000

Data Index: 230870 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6030. Min Act: -0.0000

Data Index: 564162 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 1.0900. Min Range: -1.0900

Max Act: 0.6402. Min Act: -0.0000

Data Index: 831645 (C4 (Web Text))

Max Activating Token Index: 58