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

Dataset: The Pile

Neuron 1677 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1456. Min Act: -0.0000

Data Index: 250099 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1444081 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1114. Min Act: -0.0000

Data Index: 705666 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0901. Min Act: -0.0000

Data Index: 495397 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1691319 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0803. Min Act: -0.0000

Data Index: 326283 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1496324 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1443830 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1161908 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0788. Min Act: -0.0000

Data Index: 203192 (The Pile)

Max Activating Token Index: 4

Text #10

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0708. Min Act: -0.0000

Data Index: 183003 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0840. Min Act: -0.0000

Data Index: 770516 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1673023 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0824. Min Act: -0.0000

Data Index: 629652 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1157593 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0772. Min Act: -0.0000

Data Index: 648385 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0751. Min Act: -0.0000

Data Index: 344000 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1197114 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1113985 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1189873 (The Pile)

Max Activating Token Index: 571