Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2976. Min Act: -0.0003

Data Index: 1297730 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2735. Min Act: -0.0003

Data Index: 253645 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2907. Min Act: -0.0003

Data Index: 1216848 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2765. Min Act: -0.0003

Data Index: 1038039 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2730. Min Act: -0.0003

Data Index: 625725 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2604. Min Act: -0.0003

Data Index: 793905 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2852. Min Act: -0.0003

Data Index: 1229487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2821. Min Act: -0.0003

Data Index: 1000198 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2824. Min Act: -0.0003

Data Index: 334070 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2666. Min Act: -0.0003

Data Index: 693747 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2484. Min Act: -0.0003

Data Index: 378065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2519. Min Act: -0.0003

Data Index: 198752 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2636. Min Act: -0.0003

Data Index: 741843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2411. Min Act: -0.0003

Data Index: 959083 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2516. Min Act: -0.0003

Data Index: 93038 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2604. Min Act: -0.0003

Data Index: 22046 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2544. Min Act: -0.0003

Data Index: 1291495 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2646. Min Act: -0.0003

Data Index: 871744 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2366. Min Act: -0.0003

Data Index: 317427 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2378. Min Act: -0.0003

Data Index: 268429 (C4 (Web Text))

Max Activating Token Index: 1023