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

Dataset: The Pile

Neuron 86 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1949113 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1497081 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1700245 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1858661 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4814. Min Act: -0.0000

Data Index: 89502 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4667. Min Act: -0.0000

Data Index: 915470 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4694. Min Act: -0.0000

Data Index: 298404 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1544234 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4787. Min Act: -0.0000

Data Index: 192575 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4095. Min Act: -0.0000

Data Index: 54070 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4597. Min Act: -0.0000

Data Index: 305832 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1552703 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3975. Min Act: -0.0000

Data Index: 659228 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4120. Min Act: -0.0000

Data Index: 551871 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1968005 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1782875 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1411695 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1395961 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1677225 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 0.6282. Min Range: -0.6282

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1796363 (The Pile)

Max Activating Token Index: 530