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

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

Neuron 4255 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: 0.9540. Min Range: -0.9540

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1314972 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9540. Min Act: -0.0000

Data Index: 685706 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8909. Min Act: -0.0000

Data Index: 848407 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1010588 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8781. Min Act: -0.0000

Data Index: 363567 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8799. Min Act: -0.0000

Data Index: 953719 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9116. Min Act: -0.0000

Data Index: 86278 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1157383 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1133853 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8055. Min Act: -0.0000

Data Index: 195910 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1124075 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8766. Min Act: -0.0000

Data Index: 383999 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1068355 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8772. Min Act: -0.0000

Data Index: 686039 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8513. Min Act: -0.0000

Data Index: 735099 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8733. Min Act: -0.0000

Data Index: 376632 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8754. Min Act: -0.0000

Data Index: 177173 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8542. Min Act: -0.0000

Data Index: 411072 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8335. Min Act: -0.0000

Data Index: 899680 (C4 (Web Text))

Max Activating Token Index: 517