Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2177 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.5068. Min Act: -0.0001

Data Index: 170197 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4615. Min Act: -0.0000

Data Index: 749514 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1306036 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4285. Min Act: -0.0000

Data Index: 833173 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1021545 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1258146 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4055. Min Act: -0.0000

Data Index: 697940 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1128129 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3904. Min Act: -0.0001

Data Index: 34493 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3871. Min Act: -0.0000

Data Index: 412558 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3812. Min Act: -0.0001

Data Index: 914642 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3874. Min Act: -0.0000

Data Index: 278300 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3785. Min Act: -0.0000

Data Index: 229211 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3885. Min Act: -0.0000

Data Index: 675599 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3547. Min Act: -0.0000

Data Index: 998711 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3852. Min Act: -0.0000

Data Index: 846798 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3730. Min Act: -0.0000

Data Index: 298971 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1222480 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3693. Min Act: -0.0001

Data Index: 951374 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3671. Min Act: -0.0001

Data Index: 940662 (C4 (Web Text))

Max Activating Token Index: 389