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

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

Neuron 3719 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: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0001

Data Index: 716706 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0865. Min Act: -0.0001

Data Index: 667118 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1079558 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1037637 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1175750 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1562289 (Python Code)

Max Activating Token Index: 132

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1573243 (Python Code)

Max Activating Token Index: 844

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1159595 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0784. Min Act: -0.0001

Data Index: 617410 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1220908 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0789. Min Act: -0.0001

Data Index: 850414 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1563576 (Python Code)

Max Activating Token Index: 268

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0781. Min Act: -0.0001

Data Index: 656847 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0766. Min Act: -0.0001

Data Index: 563287 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1613457 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0758. Min Act: -0.0001

Data Index: 603575 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1611343 (Python Code)

Max Activating Token Index: 977

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1032585 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1336220 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0742. Min Act: -0.0001

Data Index: 260074 (C4 (Web Text))

Max Activating Token Index: 246