Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.6343. Min Act: -0.0000

Data Index: 910693 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5936. Min Act: -0.0000

Data Index: 550235 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5935. Min Act: -0.0000

Data Index: 180076 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1727629 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1278758 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5877. Min Act: -0.0000

Data Index: 134126 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4972. Min Act: -0.0001

Data Index: 1735311 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5697. Min Act: -0.0001

Data Index: 1553691 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5488. Min Act: 0.0000

Data Index: 1261894 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5393. Min Act: -0.0000

Data Index: 99285 (The Pile)

Max Activating Token Index: 686

Text #10

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1095590 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5814. Min Act: -0.0000

Data Index: 982236 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1997211 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1716813 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5486. Min Act: -0.0000

Data Index: 104814 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1294210 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1064938 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5427. Min Act: -0.0000

Data Index: 468293 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1666360 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1442896 (The Pile)

Max Activating Token Index: 552