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

Dataset: The Pile

Neuron 1081 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.9159. Min Act: -0.0000

Data Index: 108577 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.5669. Min Act: -0.0000

Data Index: 1778219 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4869. Min Act: -0.0000

Data Index: 246304 (The Pile)

Max Activating Token Index: 936

Text #3

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4227. Min Act: -0.0000

Data Index: 1439845 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4427. Min Act: -0.0000

Data Index: 1837458 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.2683. Min Act: -0.0000

Data Index: 161846 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.1144. Min Act: -0.0000

Data Index: 582918 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.0307. Min Act: -0.0000

Data Index: 321796 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1143434 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 1.9159. Min Range: -1.9159

Max Act: 0.9997. Min Act: -0.0000

Data Index: 808621 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.2233. Min Act: -0.0000

Data Index: 389186 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1835242 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.1011. Min Act: -0.0000

Data Index: 626449 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1082028 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.0938. Min Act: -0.0000

Data Index: 511264 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.3300. Min Act: -0.0000

Data Index: 448905 (The Pile)

Max Activating Token Index: 546

Text #16

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1728999 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 1.9159. Min Range: -1.9159

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1819369 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.0231. Min Act: -0.0000

Data Index: 994639 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.9159. Min Range: -1.9159

Max Act: 0.9937. Min Act: -0.0000

Data Index: 730273 (The Pile)

Max Activating Token Index: 116