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

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

Neuron 1642 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: 0.5789. Min Range: -0.5789

Max Act: 0.5789. Min Act: -0.0002

Data Index: 998054 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5728. Min Act: -0.0002

Data Index: 592418 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5596. Min Act: -0.0002

Data Index: 295142 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5138. Min Act: -0.0002

Data Index: 230391 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5162. Min Act: -0.0003

Data Index: 46987 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4997. Min Act: -0.0002

Data Index: 205424 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5204. Min Act: -0.0002

Data Index: 264988 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5058. Min Act: -0.0002

Data Index: 215260 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5036. Min Act: -0.0002

Data Index: 226759 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4880. Min Act: -0.0002

Data Index: 1133673 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4883. Min Act: -0.0002

Data Index: 846012 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4851. Min Act: -0.0002

Data Index: 596531 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4817. Min Act: -0.0002

Data Index: 958941 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4740. Min Act: -0.0002

Data Index: 885459 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4679. Min Act: -0.0002

Data Index: 203716 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4610. Min Act: -0.0002

Data Index: 604143 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4745. Min Act: -0.0002

Data Index: 1231171 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4614. Min Act: -0.0002

Data Index: 802112 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4616. Min Act: -0.0002

Data Index: 874047 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4563. Min Act: -0.0002

Data Index: 1016896 (C4 (Web Text))

Max Activating Token Index: 320