Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3595 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1395873 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1652263 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2607. Min Act: -0.0000

Data Index: 442921 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1050326 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1471560 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2002. Min Act: -0.0000

Data Index: 466488 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2028. Min Act: -0.0000

Data Index: 827764 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2081. Min Act: -0.0000

Data Index: 227325 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1509678 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1997. Min Act: -0.0000

Data Index: 700997 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1914. Min Act: -0.0000

Data Index: 215294 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1968. Min Act: -0.0000

Data Index: 172514 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1612598 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2032. Min Act: -0.0000

Data Index: 289047 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1367136 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1845. Min Act: -0.0000

Data Index: 271453 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1891. Min Act: -0.0000

Data Index: 339089 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1812. Min Act: -0.0000

Data Index: 151517 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1858. Min Act: -0.0000

Data Index: 471419 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1862. Min Act: -0.0000

Data Index: 632271 (The Pile)

Max Activating Token Index: 133