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

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

Neuron 1036 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8757. Min Act: -0.0000

Data Index: 642195 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6520. Min Act: -0.0000

Data Index: 438833 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7796. Min Act: -0.0000

Data Index: 547991 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1075572 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7967. Min Act: -0.0000

Data Index: 607134 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7425. Min Act: -0.0000

Data Index: 150445 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6849. Min Act: -0.0000

Data Index: 48604 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1328147 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6508. Min Act: 0.0000

Data Index: 988060 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7119. Min Act: -0.0000

Data Index: 289524 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6801. Min Act: -0.0000

Data Index: 3575 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1085073 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7562. Min Act: 0.0000

Data Index: 451496 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6704. Min Act: -0.0000

Data Index: 761837 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6483. Min Act: -0.0000

Data Index: 98785 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6056. Min Act: 0.0000

Data Index: 427073 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6265. Min Act: 0.0000

Data Index: 28288 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6499. Min Act: -0.0000

Data Index: 741153 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1162163 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1137781 (C4 (Web Text))

Max Activating Token Index: 918