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

Dataset: The Pile

Neuron 4711 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: 3.9603. Min Range: -3.9603

Max Act: 3.6167. Min Act: -0.0000

Data Index: 722422 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.9603. Min Act: -0.0000

Data Index: 913091 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.6725. Min Act: -0.0000

Data Index: 1417328 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.8483. Min Act: -0.0000

Data Index: 1861286 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.6363. Min Act: -0.0000

Data Index: 1209164 (The Pile)

Max Activating Token Index: 240

Text #5

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.4634. Min Act: -0.0000

Data Index: 1994735 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2303. Min Act: -0.0000

Data Index: 190320 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.5969. Min Act: -0.0000

Data Index: 909116 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.3869. Min Act: 0.0000

Data Index: 1462500 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2048. Min Act: -0.0000

Data Index: 1068175 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2918. Min Act: -0.0000

Data Index: 1236546 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2510. Min Act: -0.0000

Data Index: 47080 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2473. Min Act: -0.0000

Data Index: 280452 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.9612. Min Act: -0.0000

Data Index: 1502619 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2277. Min Act: -0.0000

Data Index: 930989 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.8953. Min Act: -0.0000

Data Index: 586585 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.1437. Min Act: -0.0000

Data Index: 1661154 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2499. Min Act: -0.0000

Data Index: 681944 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.3025. Min Act: -0.0000

Data Index: 1584318 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.4492. Min Act: -0.0000

Data Index: 400998 (The Pile)

Max Activating Token Index: 833