Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3006 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5176. Min Act: -0.0000

Data Index: 476407 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4810. Min Act: -0.0000

Data Index: 210616 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4641. Min Act: -0.0000

Data Index: 446177 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4626. Min Act: -0.0000

Data Index: 425009 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4718. Min Act: -0.0000

Data Index: 743152 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5017. Min Act: -0.0000

Data Index: 666488 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1067925 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1029075 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4508. Min Act: -0.0000

Data Index: 430874 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4118. Min Act: -0.0000

Data Index: 643826 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4070. Min Act: -0.0000

Data Index: 102309 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1280766 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3903. Min Act: -0.0000

Data Index: 990844 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3782. Min Act: -0.0000

Data Index: 160718 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3755. Min Act: -0.0000

Data Index: 823714 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3666. Min Act: -0.0000

Data Index: 824390 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3604. Min Act: -0.0000

Data Index: 129860 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3450. Min Act: -0.0000

Data Index: 473238 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3797. Min Act: -0.0000

Data Index: 686161 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3507. Min Act: -0.0000

Data Index: 663396 (C4 (Web Text))

Max Activating Token Index: 165