Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0706. Min Act: -0.0002

Data Index: 119215 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0002

Data Index: 12373 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1058879 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0661. Min Act: -0.0002

Data Index: 688829 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0637. Min Act: -0.0002

Data Index: 498362 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0656. Min Act: -0.0002

Data Index: 890029 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0629. Min Act: -0.0002

Data Index: 914827 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0643. Min Act: -0.0002

Data Index: 64640 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0632. Min Act: -0.0002

Data Index: 97665 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1243404 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1185695 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1020110 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1145610 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1012260 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0611. Min Act: -0.0002

Data Index: 916459 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0585. Min Act: -0.0002

Data Index: 239738 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1256625 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0581. Min Act: -0.0002

Data Index: 173931 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1188407 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0600. Min Act: -0.0002

Data Index: 96245 (C4 (Web Text))

Max Activating Token Index: 76