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

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

Neuron 14 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6604. Min Act: -0.0000

Data Index: 920290 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6594. Min Act: -0.0001

Data Index: 483439 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6619. Min Act: -0.0000

Data Index: 100798 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.7075. Min Act: -0.0001

Data Index: 78715 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6550. Min Act: -0.0000

Data Index: 942394 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6688. Min Act: -0.0000

Data Index: 777036 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6270. Min Act: -0.0000

Data Index: 575865 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5813. Min Act: -0.0000

Data Index: 424885 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5949. Min Act: -0.0000

Data Index: 135278 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6096. Min Act: -0.0000

Data Index: 223812 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1249250 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6822. Min Act: -0.0000

Data Index: 688582 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5656. Min Act: -0.0000

Data Index: 989479 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6134. Min Act: -0.0000

Data Index: 327254 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1052572 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1083649 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1202745 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5329. Min Act: -0.0000

Data Index: 442730 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5799. Min Act: -0.0000

Data Index: 279813 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5386. Min Act: -0.0000

Data Index: 817053 (C4 (Web Text))

Max Activating Token Index: 794