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

Dataset: The Pile

Neuron 2027 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: 0.7775. Min Range: -0.7775

Max Act: 0.7775. Min Act: -0.0000

Data Index: 224492 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.7191. Min Act: -0.0000

Data Index: 125550 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.7502. Min Act: -0.0000

Data Index: 344405 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.7026. Min Act: -0.0000

Data Index: 662424 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6856. Min Act: -0.0000

Data Index: 634893 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1341092 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6895. Min Act: -0.0000

Data Index: 625645 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1486171 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6523. Min Act: -0.0000

Data Index: 546055 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1823449 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1949108 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6653. Min Act: -0.0000

Data Index: 22080 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.5793. Min Act: -0.0000

Data Index: 117470 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6346. Min Act: -0.0000

Data Index: 631944 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1904362 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1692052 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.5930. Min Act: -0.0000

Data Index: 263201 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1654052 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6041. Min Act: -0.0000

Data Index: 446437 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1941878 (The Pile)

Max Activating Token Index: 505