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

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

Neuron 1604 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0004

Data Index: 1262853 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0869. Min Act: -0.0004

Data Index: 1271956 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0822. Min Act: -0.0004

Data Index: 213620 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0872. Min Act: -0.0004

Data Index: 1085502 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0789. Min Act: -0.0004

Data Index: 563886 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0890. Min Act: -0.0004

Data Index: 1051694 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0819. Min Act: -0.0004

Data Index: 340457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0790. Min Act: -0.0004

Data Index: 442352 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0717. Min Act: -0.0004

Data Index: 1017990 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0729. Min Act: -0.0004

Data Index: 1289942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0685. Min Act: -0.0004

Data Index: 1158944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0727. Min Act: -0.0004

Data Index: 730594 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0650. Min Act: -0.0004

Data Index: 1133668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0671. Min Act: -0.0004

Data Index: 963428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0643. Min Act: -0.0004

Data Index: 117033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0640. Min Act: -0.0004

Data Index: 1002238 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0656. Min Act: -0.0004

Data Index: 51190 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0656. Min Act: -0.0004

Data Index: 1284836 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0649. Min Act: -0.0004

Data Index: 729028 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0676. Min Act: -0.0004

Data Index: 493341 (C4 (Web Text))

Max Activating Token Index: 1023