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

Dataset: The Pile

Neuron 2728 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8668. Min Act: -0.0000

Data Index: 867517 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1197450 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8350. Min Act: -0.0000

Data Index: 675262 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7580. Min Act: -0.0000

Data Index: 629380 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1930569 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6939. Min Act: -0.0000

Data Index: 191945 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1042293 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1939984 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6344. Min Act: -0.0000

Data Index: 328354 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6250. Min Act: -0.0000

Data Index: 266531 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6181. Min Act: -0.0000

Data Index: 333410 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6403. Min Act: -0.0000

Data Index: 357435 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1627936 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1951826 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1879385 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5539. Min Act: -0.0000

Data Index: 46249 (The Pile)

Max Activating Token Index: 868

Text #16

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1027191 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1115871 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5652. Min Act: -0.0000

Data Index: 491950 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1306039 (The Pile)

Max Activating Token Index: 858