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

Dataset: The Pile

Neuron 2731 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: 1.0048. Min Range: -1.0048

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1682677 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1241239 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1264081 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6883. Min Act: -0.0000

Data Index: 612390 (The Pile)

Max Activating Token Index: 328

Text #4

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1795971 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1332297 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7198. Min Act: -0.0000

Data Index: 876915 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1566185 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1026134 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7031. Min Act: -0.0000

Data Index: 792341 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6476. Min Act: -0.0000

Data Index: 886557 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6707. Min Act: -0.0000

Data Index: 481470 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1122073 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1335920 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6249. Min Act: -0.0000

Data Index: 809000 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6204. Min Act: -0.0000

Data Index: 40498 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7214. Min Act: -0.0000

Data Index: 701119 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1615505 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1720450 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6106. Min Act: -0.0000

Data Index: 397208 (The Pile)

Max Activating Token Index: 629