Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2919 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6379. Min Act: -0.0002

Data Index: 406504 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6167. Min Act: -0.0002

Data Index: 925952 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6341. Min Act: -0.0002

Data Index: 323617 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5734. Min Act: -0.0002

Data Index: 494989 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6113. Min Act: -0.0002

Data Index: 1451381 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5881. Min Act: -0.0002

Data Index: 187803 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6115. Min Act: -0.0002

Data Index: 1821948 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6041. Min Act: -0.0002

Data Index: 1027194 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6029. Min Act: -0.0002

Data Index: 1251443 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5679. Min Act: -0.0002

Data Index: 1866255 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5934. Min Act: -0.0002

Data Index: 1727184 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5969. Min Act: -0.0002

Data Index: 535939 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5714. Min Act: -0.0002

Data Index: 1842916 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5865. Min Act: -0.0002

Data Index: 1734168 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5789. Min Act: -0.0002

Data Index: 199136 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5830. Min Act: -0.0002

Data Index: 522791 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5806. Min Act: -0.0002

Data Index: 567662 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5992. Min Act: -0.0002

Data Index: 1605473 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6004. Min Act: -0.0002

Data Index: 513598 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5745. Min Act: -0.0002

Data Index: 36009 (The Pile)

Max Activating Token Index: 66