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

Dataset: The Pile

Neuron 930 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: 0.6219. Min Range: -0.6219

Max Act: 0.6219. Min Act: -0.0000

Data Index: 378055 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.6066. Min Act: -0.0000

Data Index: 441530 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1789613 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5706. Min Act: -0.0000

Data Index: 431843 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.6091. Min Act: -0.0000

Data Index: 246774 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1270769 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1104920 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1687753 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1274801 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1825389 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5241. Min Act: -0.0000

Data Index: 930944 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1097276 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1651975 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1167071 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5021. Min Act: -0.0000

Data Index: 231549 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4828. Min Act: -0.0000

Data Index: 226562 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1936757 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1378451 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1411570 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1383194 (The Pile)

Max Activating Token Index: 658