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

Dataset: The Pile

Neuron 1721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1830135 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1654105 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9988. Min Act: 0.0000

Data Index: 215078 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9255. Min Act: 0.0000

Data Index: 401192 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1349092 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8987. Min Act: -0.0000

Data Index: 942575 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1096591 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1434822 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8899. Min Act: -0.0000

Data Index: 862279 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1044290 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1413328 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8101. Min Act: -0.0000

Data Index: 983669 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8504. Min Act: -0.0000

Data Index: 54103 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1203403 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1661670 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1556567 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7921. Min Act: 0.0000

Data Index: 1617441 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1106507 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7879. Min Act: -0.0000

Data Index: 210811 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1937537 (The Pile)

Max Activating Token Index: 87