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

Dataset: The Pile

Neuron 2964 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2097. Min Range: -3.2097

Max Act: 3.2097. Min Act: -0.0000

Data Index: 1178881 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.6814. Min Act: -0.0000

Data Index: 1700439 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.6033. Min Act: -0.0000

Data Index: 413165 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.7002. Min Act: -0.0000

Data Index: 823746 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.7269. Min Act: -0.0000

Data Index: 269759 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.5065. Min Act: -0.0000

Data Index: 720650 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.6164. Min Act: -0.0000

Data Index: 904494 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.5206. Min Act: -0.0000

Data Index: 1957224 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.2285. Min Act: -0.0000

Data Index: 221552 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.2857. Min Act: -0.0000

Data Index: 842582 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.1486. Min Act: -0.0000

Data Index: 603287 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.1496. Min Act: -0.0000

Data Index: 894118 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.1202. Min Act: -0.0000

Data Index: 898041 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.1101. Min Act: -0.0000

Data Index: 1257833 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.2102. Min Act: -0.0000

Data Index: 1933181 (The Pile)

Max Activating Token Index: 903

Text #15

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.2057. Min Act: -0.0000

Data Index: 59126 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.1767. Min Act: -0.0000

Data Index: 1405670 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 3.2097. Min Range: -3.2097

Max Act: 2.2690. Min Act: -0.0000

Data Index: 1600255 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 3.2097. Min Range: -3.2097

Max Act: 1.9088. Min Act: -0.0000

Data Index: 1855916 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 3.2097. Min Range: -3.2097

Max Act: 1.9045. Min Act: -0.0000

Data Index: 373737 (The Pile)

Max Activating Token Index: 877