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

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

Neuron 3727 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1248961 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.5634. Min Act: -0.0000

Data Index: 752736 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.5226. Min Act: -0.0000

Data Index: 299568 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.6815. Min Act: -0.0000

Data Index: 1023523 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.5012. Min Act: -0.0000

Data Index: 101186 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.5551. Min Act: -0.0000

Data Index: 652925 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1225972 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3590. Min Act: -0.0000

Data Index: 776430 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4483. Min Act: -0.0000

Data Index: 478065 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2095. Min Act: -0.0000

Data Index: 815131 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.1933. Min Act: -0.0000

Data Index: 957234 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3520. Min Act: -0.0000

Data Index: 352884 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3694. Min Act: -0.0000

Data Index: 80684 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2759. Min Act: -0.0000

Data Index: 425478 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3289. Min Act: -0.0000

Data Index: 781013 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1127153 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1317009 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2075. Min Act: -0.0000

Data Index: 1258512 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1293436 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2331. Min Act: -0.0000

Data Index: 411319 (C4 (Web Text))

Max Activating Token Index: 976