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

Dataset: The Pile

Neuron 4618 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0000

Data Index: 83624 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0729. Min Act: 0.0000

Data Index: 1932324 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1686565 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1114112 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0711. Min Act: -0.0000

Data Index: 303638 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0697. Min Act: 0.0000

Data Index: 1489580 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1634784 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1459625 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0688. Min Act: 0.0000

Data Index: 307674 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1522798 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0682. Min Act: -0.0000

Data Index: 448662 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0658. Min Act: -0.0000

Data Index: 24268 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0682. Min Act: 0.0000

Data Index: 428218 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0670. Min Act: -0.0000

Data Index: 616948 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0665. Min Act: 0.0000

Data Index: 1311213 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0658. Min Act: -0.0000

Data Index: 231938 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0656. Min Act: 0.0001

Data Index: 56994 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0651. Min Act: 0.0000

Data Index: 1576063 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0649. Min Act: 0.0000

Data Index: 1793466 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1454163 (The Pile)

Max Activating Token Index: 1023