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

Dataset: The Pile

Neuron 3087 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0127. Min Range: -1.0127

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1994085 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8710. Min Act: -0.0000

Data Index: 129981 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7030. Min Act: -0.0000

Data Index: 432324 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7264. Min Act: -0.0000

Data Index: 163509 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1570821 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1514696 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7237. Min Act: -0.0000

Data Index: 126614 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6851. Min Act: -0.0000

Data Index: 184507 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1815438 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1116818 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1114792 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5760. Min Act: -0.0000

Data Index: 522730 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1173129 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1293542 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6679. Min Act: -0.0000

Data Index: 499347 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6168. Min Act: -0.0000

Data Index: 656779 (The Pile)

Max Activating Token Index: 20

Text #16

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1767340 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5305. Min Act: -0.0000

Data Index: 313417 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5609. Min Act: -0.0000

Data Index: 775092 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5947. Min Act: -0.0000

Data Index: 72354 (The Pile)

Max Activating Token Index: 301