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

Dataset: The Pile

Neuron 2287 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1280044 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6776. Min Act: -0.0000

Data Index: 232361 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1952352 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5886. Min Act: -0.0000

Data Index: 889467 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5908. Min Act: -0.0000

Data Index: 999352 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1497026 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1020122 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5728. Min Act: -0.0000

Data Index: 25956 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1277192 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4471. Min Act: -0.0000

Data Index: 597125 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1820645 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1592128 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1836308 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4191. Min Act: -0.0000

Data Index: 383671 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1196470 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1065949 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.3937. Min Act: -0.0000

Data Index: 966727 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1287263 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.4572. Min Act: -0.0000

Data Index: 97751 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1139041 (The Pile)

Max Activating Token Index: 1000