Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 239 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0001

Data Index: 789632 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1092125 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1263373 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1330421 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0693. Min Act: -0.0001

Data Index: 99987 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0788. Min Act: -0.0001

Data Index: 738754 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0728. Min Act: -0.0001

Data Index: 123886 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0667. Min Act: -0.0001

Data Index: 675581 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0663. Min Act: -0.0001

Data Index: 653127 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1049373 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0637. Min Act: -0.0001

Data Index: 983218 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0609. Min Act: -0.0001

Data Index: 107866 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1047429 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1233162 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0612. Min Act: -0.0001

Data Index: 73353 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0684. Min Act: -0.0001

Data Index: 511507 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0604. Min Act: -0.0001

Data Index: 565908 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0629. Min Act: -0.0001

Data Index: 659834 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1210952 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0557. Min Act: -0.0001

Data Index: 62818 (C4 (Web Text))

Max Activating Token Index: 348