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

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

Neuron 2755 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5638. Min Act: -0.0001

Data Index: 554746 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5613. Min Act: -0.0001

Data Index: 52778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5365. Min Act: -0.0001

Data Index: 1214586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4937. Min Act: -0.0001

Data Index: 442619 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4962. Min Act: -0.0001

Data Index: 467745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5023. Min Act: -0.0001

Data Index: 516268 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4924. Min Act: -0.0001

Data Index: 170363 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4924. Min Act: -0.0001

Data Index: 907248 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4766. Min Act: -0.0001

Data Index: 709233 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4911. Min Act: -0.0001

Data Index: 1316927 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4826. Min Act: -0.0001

Data Index: 30126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4734. Min Act: -0.0001

Data Index: 1004285 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4753. Min Act: -0.0001

Data Index: 1008270 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4818. Min Act: -0.0001

Data Index: 111085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4735. Min Act: -0.0001

Data Index: 331835 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4773. Min Act: -0.0001

Data Index: 103213 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4727. Min Act: -0.0001

Data Index: 744813 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4637. Min Act: -0.0001

Data Index: 414947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4666. Min Act: -0.0001

Data Index: 818161 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4583. Min Act: -0.0001

Data Index: 1325865 (C4 (Web Text))

Max Activating Token Index: 1023