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

Dataset: The Pile

Neuron 152 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: 1.0012. Min Range: -1.0012

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1754320 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8265. Min Act: -0.0000

Data Index: 636993 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7613. Min Act: -0.0000

Data Index: 733797 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1716182 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7230. Min Act: -0.0000

Data Index: 44539 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7167. Min Act: -0.0000

Data Index: 613549 (The Pile)

Max Activating Token Index: 3

Text #6

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1882125 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7346. Min Act: -0.0000

Data Index: 622309 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7287. Min Act: -0.0000

Data Index: 701662 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7129. Min Act: -0.0000

Data Index: 714378 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1663949 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1126357 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7004. Min Act: -0.0000

Data Index: 253992 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6952. Min Act: -0.0000

Data Index: 337665 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6603. Min Act: -0.0001

Data Index: 1232470 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6804. Min Act: -0.0000

Data Index: 219455 (The Pile)

Max Activating Token Index: 6

Text #16

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1957652 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1828134 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1441282 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6742. Min Act: -0.0000

Data Index: 979797 (The Pile)

Max Activating Token Index: 3