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

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

Neuron 4522 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: 0.6660. Min Range: -0.6660

Max Act: 0.6484. Min Act: -0.0000

Data Index: 676914 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1085874 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1016121 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5729. Min Act: -0.0000

Data Index: 416533 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5650. Min Act: -0.0000

Data Index: 716802 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5288. Min Act: -0.0000

Data Index: 531094 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5287. Min Act: -0.0000

Data Index: 840386 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5225. Min Act: -0.0000

Data Index: 474765 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5345. Min Act: -0.0000

Data Index: 95773 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5446. Min Act: -0.0000

Data Index: 585542 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5440. Min Act: -0.0000

Data Index: 42987 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5041. Min Act: -0.0000

Data Index: 2687 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4965. Min Act: -0.0000

Data Index: 690082 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1086689 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4872. Min Act: -0.0000

Data Index: 831223 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4882. Min Act: -0.0000

Data Index: 64112 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4992. Min Act: -0.0000

Data Index: 623031 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4974. Min Act: -0.0000

Data Index: 174214 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4763. Min Act: -0.0000

Data Index: 33492 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4902. Min Act: -0.0000

Data Index: 187208 (C4 (Web Text))

Max Activating Token Index: 95