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

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

Neuron 1016 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: 0.9848. Min Range: -0.9848

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1646956 (Python Code)

Max Activating Token Index: 217

Text #1

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.9137. Min Act: -0.0000

Data Index: 170010 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8981. Min Act: -0.0000

Data Index: 591760 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1579787 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1062134 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7789. Min Act: -0.0000

Data Index: 45544 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8240. Min Act: -0.0000

Data Index: 908163 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7749. Min Act: -0.0000

Data Index: 238249 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1264949 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7778. Min Act: -0.0000

Data Index: 329303 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1538333 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7879. Min Act: -0.0000

Data Index: 731106 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7309. Min Act: -0.0000

Data Index: 561731 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1387134 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1457097 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1383189 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6903. Min Act: -0.0000

Data Index: 733694 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1342768 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1589744 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7155. Min Act: -0.0000

Data Index: 839728 (C4 (Web Text))

Max Activating Token Index: 6