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

Dataset: The Pile

Neuron 1843 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: 1.8540. Min Range: -1.8540

Max Act: 1.8540. Min Act: -0.0000

Data Index: 89370 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.2547. Min Act: -0.0000

Data Index: 1036686 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.1418. Min Act: -0.0000

Data Index: 916970 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.1274. Min Act: -0.0000

Data Index: 618947 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1128987 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.9643. Min Act: -0.0000

Data Index: 628263 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.8829. Min Act: -0.0000

Data Index: 866461 (The Pile)

Max Activating Token Index: 804

Text #7

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1153156 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.8296. Min Act: -0.0000

Data Index: 13541 (The Pile)

Max Activating Token Index: 772

Text #9

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1661628 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.8722. Min Act: -0.0000

Data Index: 70753 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.8939. Min Act: -0.0000

Data Index: 119121 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1009767 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.9014. Min Act: -0.0000

Data Index: 893266 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.7208. Min Act: -0.0000

Data Index: 219546 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.7945. Min Act: -0.0000

Data Index: 480222 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1336305 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1749298 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1277000 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.8540. Min Range: -1.8540

Max Act: 0.6706. Min Act: -0.0000

Data Index: 633182 (The Pile)

Max Activating Token Index: 694