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

Dataset: The Pile

Neuron 4128 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1377. Min Act: -0.0000

Data Index: 601126 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1348. Min Act: -0.0000

Data Index: 983603 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1141. Min Act: -0.0000

Data Index: 575084 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1501991 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1000. Min Act: -0.0000

Data Index: 164310 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0828. Min Act: -0.0000

Data Index: 665854 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1017122 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1582544 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1924689 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1745754 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1407748 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1994057 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1428519 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1747736 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0947. Min Act: -0.0000

Data Index: 124751 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1558658 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0875. Min Act: -0.0000

Data Index: 145691 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1989946 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1763781 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0860. Min Act: -0.0000

Data Index: 134699 (The Pile)

Max Activating Token Index: 955