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

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

Neuron 62 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0003

Data Index: 962460 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1656189 (Python Code)

Max Activating Token Index: 756

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0003

Data Index: 350748 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0003

Data Index: 45794 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1617 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1082704 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1011826 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0003

Data Index: 519788 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0003

Data Index: 822602 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0003

Data Index: 936198 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0049. Min Act: -0.0003

Data Index: 531224 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0049. Min Act: -0.0003

Data Index: 329171 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1166993 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0049. Min Act: -0.0003

Data Index: 306097 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0049. Min Act: -0.0003

Data Index: 769159 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0049. Min Act: -0.0003

Data Index: 954879 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1215465 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1427186 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1007617 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1031329 (C4 (Web Text))

Max Activating Token Index: 122