Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0908. Min Act: -0.0001

Data Index: 229686 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0001

Data Index: 352935 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0817. Min Act: -0.0001

Data Index: 46023 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0816. Min Act: -0.0001

Data Index: 450356 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0812. Min Act: -0.0001

Data Index: 929881 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1136310 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0762. Min Act: -0.0001

Data Index: 724200 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1121307 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0707. Min Act: -0.0001

Data Index: 434525 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1266961 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0696. Min Act: -0.0001

Data Index: 883921 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0715. Min Act: -0.0001

Data Index: 912046 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0685. Min Act: -0.0001

Data Index: 945634 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0701. Min Act: -0.0001

Data Index: 200700 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0683. Min Act: -0.0001

Data Index: 289688 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0668. Min Act: -0.0001

Data Index: 309856 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1183077 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0688. Min Act: -0.0001

Data Index: 381745 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0675. Min Act: -0.0001

Data Index: 1103240 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1210350 (C4 (Web Text))

Max Activating Token Index: 89