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

Dataset: The Pile

Neuron 3505 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: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0000

Data Index: 162886 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1442865 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1531. Min Act: -0.0000

Data Index: 1785065 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1128090 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1230. Min Act: -0.0000

Data Index: 546088 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1596968 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1086435 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1040613 (The Pile)

Max Activating Token Index: 285

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1236. Min Act: -0.0000

Data Index: 991273 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1122. Min Act: -0.0000

Data Index: 750704 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1607948 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1424572 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1196862 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1144. Min Act: -0.0000

Data Index: 660398 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1077932 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1230. Min Act: -0.0000

Data Index: 335977 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1396148 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1807686 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1014. Min Act: -0.0000

Data Index: 798943 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1024991 (The Pile)

Max Activating Token Index: 298