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

Dataset: The Pile

Neuron 3170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8992. Min Act: -0.0000

Data Index: 982999 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1068936 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1853149 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7647. Min Act: -0.0000

Data Index: 814330 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1514476 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1879576 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6062. Min Act: -0.0000

Data Index: 694028 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1410232 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.5998. Min Act: -0.0000

Data Index: 315100 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1972899 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7095. Min Act: -0.0000

Data Index: 367410 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1434620 (The Pile)

Max Activating Token Index: 618

Text #12

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.5554. Min Act: -0.0000

Data Index: 425572 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.5862. Min Act: -0.0000

Data Index: 560213 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6413. Min Act: -0.0000

Data Index: 466995 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6287. Min Act: -0.0000

Data Index: 250613 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.5928. Min Act: -0.0000

Data Index: 353929 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6285. Min Act: -0.0000

Data Index: 715348 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6201. Min Act: -0.0000

Data Index: 112364 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.5486. Min Act: -0.0000

Data Index: 704337 (The Pile)

Max Activating Token Index: 886