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

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

Neuron 724 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: 2.2662. Min Range: -2.2662

Max Act: 2.2662. Min Act: -0.0000

Data Index: 638047 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 2.2662. Min Range: -2.2662

Max Act: 2.1654. Min Act: -0.0000

Data Index: 350207 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 2.2662. Min Range: -2.2662

Max Act: 2.1396. Min Act: -0.0000

Data Index: 1257954 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.8247. Min Act: -0.0000

Data Index: 1318982 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.6691. Min Act: 0.0000

Data Index: 441839 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.6075. Min Act: -0.0000

Data Index: 978639 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.5002. Min Act: -0.0000

Data Index: 857468 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.3615. Min Act: -0.0000

Data Index: 77392 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.3137. Min Act: -0.0000

Data Index: 433977 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.3423. Min Act: -0.0000

Data Index: 550841 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.2581. Min Act: -0.0000

Data Index: 431658 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1203689 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.2251. Min Act: -0.0000

Data Index: 697067 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.2145. Min Act: 0.0000

Data Index: 1055856 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.1885. Min Act: -0.0000

Data Index: 22360 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.1884. Min Act: -0.0000

Data Index: 48359 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.1718. Min Act: -0.0000

Data Index: 878249 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.1715. Min Act: -0.0000

Data Index: 2263 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.0920. Min Act: -0.0000

Data Index: 408082 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 2.2662. Min Range: -2.2662

Max Act: 1.1471. Min Act: -0.0000

Data Index: 112553 (C4 (Web Text))

Max Activating Token Index: 721