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

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

Neuron 3686 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0581. Min Range: -1.0581

Max Act: 1.0581. Min Act: -0.0000

Data Index: 758544 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8891. Min Act: -0.0000

Data Index: 183198 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8643. Min Act: -0.0000

Data Index: 395639 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8141. Min Act: -0.0000

Data Index: 189662 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1231133 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1041712 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7609. Min Act: -0.0000

Data Index: 291691 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7561. Min Act: -0.0000

Data Index: 20659 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1062430 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7523. Min Act: -0.0000

Data Index: 530821 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7524. Min Act: -0.0000

Data Index: 598826 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7465. Min Act: -0.0000

Data Index: 438093 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1089270 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7307. Min Act: -0.0000

Data Index: 901279 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1239000 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1229376 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7173. Min Act: -0.0000

Data Index: 272147 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7059. Min Act: -0.0000

Data Index: 92530 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7025. Min Act: -0.0000

Data Index: 785340 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1270125 (C4 (Web Text))

Max Activating Token Index: 426