Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1066 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0042. Min Act: -0.0001

Data Index: 845524 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0203. Min Act: -0.0001

Data Index: 130341 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0673. Min Act: -0.0001

Data Index: 870759 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9735. Min Act: -0.0001

Data Index: 1195548 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9141. Min Act: -0.0001

Data Index: 291833 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8104. Min Act: -0.0001

Data Index: 782099 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7321. Min Act: -0.0001

Data Index: 98132 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8786. Min Act: -0.0001

Data Index: 1237667 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8989. Min Act: -0.0001

Data Index: 1344877 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8485. Min Act: -0.0001

Data Index: 31794 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7324. Min Act: -0.0001

Data Index: 535176 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8428. Min Act: -0.0001

Data Index: 964007 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8112. Min Act: -0.0001

Data Index: 436113 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7789. Min Act: -0.0001

Data Index: 1130865 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8050. Min Act: -0.0001

Data Index: 1124266 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8167. Min Act: -0.0001

Data Index: 778362 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7688. Min Act: -0.0001

Data Index: 1278149 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8119. Min Act: -0.0001

Data Index: 419539 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8128. Min Act: -0.0001

Data Index: 648093 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8219. Min Act: -0.0001

Data Index: 1208692 (C4 (Web Text))

Max Activating Token Index: 724