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

Dataset: The Pile

Neuron 4267 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.7135. Min Act: -0.0000

Data Index: 590396 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.7734. Min Act: -0.0000

Data Index: 1525856 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.8170. Min Act: -0.0000

Data Index: 910158 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1441529 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1897663 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4618. Min Act: -0.0000

Data Index: 838616 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.6050. Min Act: -0.0000

Data Index: 361913 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.5608. Min Act: -0.0000

Data Index: 1809642 (The Pile)

Max Activating Token Index: 12

Text #8

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4999. Min Act: -0.0000

Data Index: 52180 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.5399. Min Act: -0.0000

Data Index: 917031 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.6110. Min Act: -0.0000

Data Index: 54123 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.5123. Min Act: -0.0000

Data Index: 470865 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.6401. Min Act: -0.0000

Data Index: 806844 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.3413. Min Act: -0.0000

Data Index: 861509 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1162347 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.3679. Min Act: -0.0000

Data Index: 1578958 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1349492 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1648267 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1730688 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.3210. Min Act: -0.0000

Data Index: 175887 (The Pile)

Max Activating Token Index: 659