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

Dataset: The Pile

Neuron 3308 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: 1.7685. Min Range: -1.7685

Max Act: 1.7685. Min Act: -0.0000

Data Index: 1947498 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.3993. Min Act: -0.0000

Data Index: 323946 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.2361. Min Act: -0.0000

Data Index: 920145 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.2984. Min Act: -0.0000

Data Index: 1054375 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.1896. Min Act: -0.0000

Data Index: 844050 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1145123 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.1500. Min Act: -0.0000

Data Index: 195782 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.0973. Min Act: -0.0000

Data Index: 584687 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1992118 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.0857. Min Act: -0.0001

Data Index: 1803289 (The Pile)

Max Activating Token Index: 782

Text #10

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1458646 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1140972 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.1225. Min Act: -0.0000

Data Index: 37799 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 1.7685. Min Range: -1.7685

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1054321 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 1.7685. Min Range: -1.7685

Max Act: 0.9921. Min Act: -0.0000

Data Index: 584222 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 1.7685. Min Range: -1.7685

Max Act: 0.9510. Min Act: -0.0000

Data Index: 527174 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 1.7685. Min Range: -1.7685

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1703668 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 1.7685. Min Range: -1.7685

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1704743 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 1.7685. Min Range: -1.7685

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1961875 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 1.7685. Min Range: -1.7685

Max Act: 0.9104. Min Act: -0.0000

Data Index: 62922 (The Pile)

Max Activating Token Index: 410