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

Dataset: The Pile

Neuron 1051 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: 1.4054. Min Range: -1.4054

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1462780 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1781199 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3805. Min Act: -0.0000

Data Index: 651799 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.0252. Min Act: -0.0000

Data Index: 645262 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1343063 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1551. Min Act: 0.0000

Data Index: 1681901 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1213405 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1036715 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9335. Min Act: 0.0001

Data Index: 474020 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9047. Min Act: -0.0000

Data Index: 482635 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1972081 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8847. Min Act: -0.0000

Data Index: 676326 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9200. Min Act: 0.0000

Data Index: 305170 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1308417 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9655. Min Act: 0.0000

Data Index: 1739740 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1900316 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7745. Min Act: -0.0000

Data Index: 738271 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9285. Min Act: -0.0000

Data Index: 360737 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8747. Min Act: -0.0000

Data Index: 751173 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1354005 (The Pile)

Max Activating Token Index: 522