Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3477 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1497098 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1684493 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1342096 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6475. Min Act: -0.0000

Data Index: 658046 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6515. Min Act: -0.0000

Data Index: 719145 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6433. Min Act: -0.0000

Data Index: 169662 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1851213 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5919. Min Act: -0.0000

Data Index: 236895 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1756345 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6603. Min Act: -0.0000

Data Index: 962081 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6407. Min Act: -0.0000

Data Index: 168474 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1372788 (The Pile)

Max Activating Token Index: 865

Text #12

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6162. Min Act: -0.0000

Data Index: 868002 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1233948 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1307528 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6376. Min Act: -0.0000

Data Index: 676183 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1588140 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6521. Min Act: 0.0000

Data Index: 1678398 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1569155 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6251. Min Act: -0.0000

Data Index: 989112 (The Pile)

Max Activating Token Index: 369