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

Dataset: The Pile

Neuron 2036 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: 0.7214. Min Range: -0.7214

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1495580 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.7214. Min Act: -0.0000

Data Index: 191903 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.7032. Min Act: -0.0000

Data Index: 601485 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6898. Min Act: -0.0000

Data Index: 224328 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1244624 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1904706 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6964. Min Act: -0.0000

Data Index: 215548 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1052907 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1672004 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6041. Min Act: -0.0000

Data Index: 737909 (The Pile)

Max Activating Token Index: 29

Text #10

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5622. Min Act: -0.0000

Data Index: 346096 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6050. Min Act: -0.0000

Data Index: 393377 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5770. Min Act: -0.0000

Data Index: 600807 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1566040 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1524942 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1170209 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5735. Min Act: -0.0000

Data Index: 334834 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5202. Min Act: -0.0000

Data Index: 726748 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6106. Min Act: -0.0000

Data Index: 339810 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1630904 (The Pile)

Max Activating Token Index: 82