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

Dataset: The Pile

Neuron 4182 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: 1.3603. Min Range: -1.3603

Max Act: 1.3130. Min Act: -0.0000

Data Index: 580134 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1265170 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1119591 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1527519 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0893. Min Act: -0.0000

Data Index: 684164 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1494. Min Act: -0.0000

Data Index: 536232 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1013. Min Act: -0.0000

Data Index: 85931 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1069007 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0961. Min Act: -0.0000

Data Index: 550920 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1227576 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1096518 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1081. Min Act: -0.0000

Data Index: 302067 (The Pile)

Max Activating Token Index: 770

Text #12

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0086. Min Act: -0.0000

Data Index: 776935 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0704. Min Act: -0.0000

Data Index: 485329 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1228108 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1438040 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1965099 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1085607 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0548. Min Act: -0.0000

Data Index: 988089 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1065544 (The Pile)

Max Activating Token Index: 766