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

Dataset: The Pile

Neuron 1895 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: 1.3695. Min Range: -1.3695

Max Act: 1.3695. Min Act: -0.0000

Data Index: 1561475 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1173634 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1367. Min Act: -0.0000

Data Index: 1170936 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1062626 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.9917. Min Act: -0.0000

Data Index: 49562 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1552978 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1178003 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1494679 (The Pile)

Max Activating Token Index: 971

Text #8

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1611379 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0029. Min Act: -0.0000

Data Index: 798339 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1643847 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.8524. Min Act: -0.0000

Data Index: 397198 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1718154 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0129. Min Act: -0.0000

Data Index: 458350 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1294876 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0648. Min Act: -0.0000

Data Index: 673462 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1120622 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1210259 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1443277 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1303499 (The Pile)

Max Activating Token Index: 500