Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3639 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.7693. Min Act: -0.0000

Data Index: 504088 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.7191. Min Act: -0.0000

Data Index: 313784 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1134055 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1100599 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5817. Min Act: -0.0000

Data Index: 463444 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5803. Min Act: -0.0000

Data Index: 908945 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5721. Min Act: -0.0001

Data Index: 1224490 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5674. Min Act: -0.0000

Data Index: 718892 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5616. Min Act: -0.0000

Data Index: 260915 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5555. Min Act: -0.0001

Data Index: 439932 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5463. Min Act: -0.0001

Data Index: 332620 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5410. Min Act: -0.0001

Data Index: 353928 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5189. Min Act: -0.0000

Data Index: 704161 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1036213 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.4878. Min Act: -0.0000

Data Index: 250852 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5024. Min Act: -0.0001

Data Index: 740359 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.4869. Min Act: -0.0001

Data Index: 38925 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1262432 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.4866. Min Act: -0.0000

Data Index: 746951 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.4998. Min Act: -0.0000

Data Index: 715815 (C4 (Web Text))

Max Activating Token Index: 498