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

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

Neuron 4283 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9781. Min Act: -0.0001

Data Index: 3714 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9910. Min Act: -0.0001

Data Index: 785886 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9523. Min Act: -0.0001

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9105. Min Act: -0.0001

Data Index: 1110195 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9156. Min Act: -0.0001

Data Index: 360632 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8732. Min Act: -0.0001

Data Index: 54785 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7892. Min Act: -0.0001

Data Index: 560087 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8317. Min Act: -0.0001

Data Index: 626135 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7149. Min Act: -0.0001

Data Index: 648643 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7142. Min Act: -0.0001

Data Index: 332759 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7079. Min Act: -0.0001

Data Index: 535542 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7933. Min Act: -0.0001

Data Index: 1017545 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7180. Min Act: -0.0001

Data Index: 1280799 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.6216. Min Act: -0.0001

Data Index: 279036 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7063. Min Act: -0.0001

Data Index: 1292713 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.6975. Min Act: -0.0001

Data Index: 992240 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1027078 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.6487. Min Act: -0.0001

Data Index: 238355 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.6562. Min Act: -0.0001

Data Index: 915526 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.6376. Min Act: -0.0001

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 849