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

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

Neuron 892 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.2875. Min Act: -0.0000

Data Index: 166032 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.2631. Min Act: -0.0000

Data Index: 336366 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1019. Min Act: -0.0000

Data Index: 698015 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0532. Min Act: -0.0000

Data Index: 156506 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1233355 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0393. Min Act: -0.0000

Data Index: 783873 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0591. Min Act: -0.0000

Data Index: 269837 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0143. Min Act: -0.0000

Data Index: 437188 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1321433 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9708. Min Act: -0.0000

Data Index: 540533 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1339149 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9847. Min Act: -0.0000

Data Index: 535306 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1108995 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9589. Min Act: -0.0000

Data Index: 24446 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0064. Min Act: -0.0000

Data Index: 39362 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9030. Min Act: -0.0000

Data Index: 757708 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.8976. Min Act: -0.0000

Data Index: 110315 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.8681. Min Act: -0.0000

Data Index: 200904 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.8955. Min Act: -0.0000

Data Index: 827586 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9117. Min Act: -0.0000

Data Index: 345048 (C4 (Web Text))

Max Activating Token Index: 523