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

Dataset: The Pile

Neuron 2593 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: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1113735 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1379974 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1960486 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0652. Min Act: -0.0000

Data Index: 40147 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0652. Min Act: -0.0000

Data Index: 221585 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0652. Min Act: -0.0000

Data Index: 753963 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0651. Min Act: -0.0000

Data Index: 524926 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0650. Min Act: -0.0000

Data Index: 229430 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0647. Min Act: -0.0000

Data Index: 179542 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1839383 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0620. Min Act: -0.0000

Data Index: 342954 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0644. Min Act: -0.0000

Data Index: 168015 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0639. Min Act: -0.0000

Data Index: 460784 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1106309 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0639. Min Act: -0.0000

Data Index: 915229 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1877039 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1737856 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1133941 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0637. Min Act: -0.0000

Data Index: 772842 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0636. Min Act: -0.0000

Data Index: 448601 (The Pile)

Max Activating Token Index: 1023