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

Dataset: The Pile

Neuron 1335 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: 1.6117. Min Range: -1.6117

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1979063 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1656977 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1593353 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.3889. Min Act: -0.0000

Data Index: 1213648 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1613944 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1697. Min Act: -0.0000

Data Index: 366937 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2066. Min Act: -0.0000

Data Index: 265776 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1803533 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1664370 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1871185 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1425. Min Act: -0.0000

Data Index: 887325 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1831192 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1583927 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1108. Min Act: -0.0000

Data Index: 512154 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 1.6117. Min Range: -1.6117

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1758893 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.1268. Min Act: -0.0000

Data Index: 781535 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1580751 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.0242. Min Act: -0.0000

Data Index: 870950 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.0346. Min Act: -0.0000

Data Index: 490440 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.6117. Min Range: -1.6117

Max Act: 1.0593. Min Act: -0.0000

Data Index: 660585 (The Pile)

Max Activating Token Index: 596