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

Dataset: The Pile

Neuron 4035 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: 0.1603. Min Range: -0.1603

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1233128 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1249474 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1335. Min Act: -0.0000

Data Index: 611355 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1279. Min Act: -0.0000

Data Index: 694610 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1126. Min Act: -0.0000

Data Index: 674699 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1511099 (The Pile)

Max Activating Token Index: 813

Text #6

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1219. Min Act: -0.0000

Data Index: 490456 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1092. Min Act: -0.0000

Data Index: 266257 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1268004 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1339064 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.0985. Min Act: -0.0000

Data Index: 814247 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1097. Min Act: -0.0000

Data Index: 194207 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1015. Min Act: -0.0000

Data Index: 487823 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1967971 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1218068 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.0947. Min Act: -0.0000

Data Index: 121352 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1392058 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.0965. Min Act: -0.0000

Data Index: 758889 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1044655 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 0.1603. Min Range: -0.1603

Max Act: 0.0952. Min Act: -0.0000

Data Index: 60937 (The Pile)

Max Activating Token Index: 767