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

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

Neuron 1923 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.7846. Min Act: -0.0000

Data Index: 227904 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.4026. Min Act: -0.0000

Data Index: 463320 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.1896. Min Act: -0.0000

Data Index: 884729 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.4980. Min Act: -0.0000

Data Index: 106476 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.4854. Min Act: -0.0000

Data Index: 356882 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.2686. Min Act: -0.0000

Data Index: 808126 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.3974. Min Act: -0.0000

Data Index: 76251 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.5117. Min Act: -0.0000

Data Index: 1202737 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.3626. Min Act: -0.0000

Data Index: 616242 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.2608. Min Act: -0.0000

Data Index: 1037335 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.2903. Min Act: -0.0000

Data Index: 1190115 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.3340. Min Act: -0.0000

Data Index: 1174595 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.1745. Min Act: -0.0000

Data Index: 1101088 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.1700. Min Act: -0.0000

Data Index: 179454 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.2804. Min Act: -0.0000

Data Index: 1352973 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.0212. Min Act: -0.0000

Data Index: 117832 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.0939. Min Act: -0.0000

Data Index: 234987 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.1057. Min Act: -0.0000

Data Index: 817234 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.0604. Min Act: -0.0000

Data Index: 548012 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 2.7846. Min Range: -2.7846

Max Act: 2.1735. Min Act: -0.0000

Data Index: 308613 (C4 (Web Text))

Max Activating Token Index: 101