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

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

Neuron 4654 in Layer 1

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: 0.8829. Min Range: -0.8829

Max Act: 0.8829. Min Act: -0.0002

Data Index: 1170891 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7588. Min Act: -0.0002

Data Index: 666659 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7208. Min Act: -0.0002

Data Index: 16554 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7172. Min Act: -0.0002

Data Index: 49894 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7113. Min Act: -0.0002

Data Index: 205732 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7083. Min Act: -0.0002

Data Index: 828966 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7121. Min Act: -0.0002

Data Index: 363401 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7014. Min Act: -0.0002

Data Index: 1287665 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6950. Min Act: -0.0002

Data Index: 1149420 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6932. Min Act: -0.0002

Data Index: 394550 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6837. Min Act: -0.0002

Data Index: 666090 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6713. Min Act: -0.0002

Data Index: 167061 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6807. Min Act: -0.0002

Data Index: 961189 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6865. Min Act: -0.0002

Data Index: 1237988 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6709. Min Act: -0.0002

Data Index: 963499 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6652. Min Act: -0.0002

Data Index: 285702 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6575. Min Act: -0.0002

Data Index: 813433 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6610. Min Act: -0.0002

Data Index: 740668 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6433. Min Act: -0.0002

Data Index: 8838 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6552. Min Act: -0.0002

Data Index: 994700 (C4 (Web Text))

Max Activating Token Index: 139