Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 921 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0988. Min Range: -1.0988

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1967995 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1955584 (The Pile)

Max Activating Token Index: 879

Text #2

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.9375. Min Act: -0.0000

Data Index: 430642 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8143. Min Act: -0.0000

Data Index: 94964 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1682847 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8300. Min Act: -0.0000

Data Index: 645990 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8224. Min Act: -0.0000

Data Index: 234543 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8123. Min Act: -0.0000

Data Index: 218882 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8412. Min Act: -0.0000

Data Index: 214950 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7918. Min Act: -0.0000

Data Index: 201968 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7843. Min Act: -0.0000

Data Index: 437543 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7804. Min Act: -0.0000

Data Index: 92119 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.6000. Min Act: -0.0000

Data Index: 918851 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1300640 (The Pile)

Max Activating Token Index: 966

Text #14

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7236. Min Act: -0.0000

Data Index: 834081 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7987. Min Act: -0.0000

Data Index: 767334 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7684. Min Act: -0.0000

Data Index: 280982 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1748778 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1754664 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1472012 (The Pile)

Max Activating Token Index: 712