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

Dataset: The Pile

Neuron 851 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: 1.2078. Min Range: -1.2078

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1933972 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1347954 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0976. Min Act: -0.0000

Data Index: 730168 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1047434 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0581. Min Act: -0.0000

Data Index: 940962 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.1474. Min Act: -0.0000

Data Index: 174291 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.1599. Min Act: -0.0000

Data Index: 459625 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1728634 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1291280 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1761434 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1021834 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1967420 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9257. Min Act: -0.0000

Data Index: 911957 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1753144 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1422253 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1311482 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1411166 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1906202 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1123881 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9596. Min Act: -0.0000

Data Index: 884680 (The Pile)

Max Activating Token Index: 159