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

Dataset: The Pile

Neuron 2422 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.6000. Min Act: -0.0000

Data Index: 364100 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1797514 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1130633 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.5219. Min Act: -0.0000

Data Index: 846665 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1352563 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.3052. Min Act: -0.0000

Data Index: 562167 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2310. Min Act: 0.0000

Data Index: 281608 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2737. Min Act: 0.0000

Data Index: 410835 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.1883. Min Act: 0.0000

Data Index: 1855940 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.1281. Min Act: -0.0000

Data Index: 1022630 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1981332 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1426975 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.1996. Min Act: 0.0000

Data Index: 1488297 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1214455 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1420727 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 1.6000. Min Range: -1.6000

Max Act: 0.9892. Min Act: -0.0000

Data Index: 301851 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.0627. Min Act: 0.0000

Data Index: 110434 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 1.6000. Min Range: -1.6000

Max Act: 0.9299. Min Act: -0.0000

Data Index: 689011 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.1243. Min Act: -0.0000

Data Index: 773179 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.0806. Min Act: -0.0000

Data Index: 777038 (The Pile)

Max Activating Token Index: 760