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

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

Neuron 2724 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.9014. Min Act: -0.0001

Data Index: 904901 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.9785. Min Act: -0.0001

Data Index: 770622 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8966. Min Act: -0.0001

Data Index: 600600 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8939. Min Act: -0.0001

Data Index: 960033 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8711. Min Act: -0.0001

Data Index: 24009 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8746. Min Act: -0.0001

Data Index: 702877 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8666. Min Act: -0.0001

Data Index: 1343838 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8749. Min Act: -0.0001

Data Index: 1113652 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8735. Min Act: -0.0001

Data Index: 264899 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8215. Min Act: -0.0001

Data Index: 603965 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8172. Min Act: -0.0001

Data Index: 1228921 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8692. Min Act: -0.0001

Data Index: 905573 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8440. Min Act: -0.0001

Data Index: 741061 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8990. Min Act: -0.0001

Data Index: 1007277 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8687. Min Act: -0.0001

Data Index: 215762 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8063. Min Act: -0.0001

Data Index: 1009946 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8920. Min Act: -0.0001

Data Index: 828583 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7871. Min Act: -0.0001

Data Index: 1265874 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7799. Min Act: -0.0001

Data Index: 722958 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8022. Min Act: -0.0001

Data Index: 569208 (C4 (Web Text))

Max Activating Token Index: 917