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

Dataset: The Pile

Neuron 996 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.8931. Min Act: -0.0000

Data Index: 301489 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.7608. Min Act: -0.0000

Data Index: 537466 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.8228. Min Act: -0.0000

Data Index: 1661212 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.5070. Min Act: -0.0000

Data Index: 807909 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.1518. Min Act: -0.0000

Data Index: 533386 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.0306. Min Act: -0.0000

Data Index: 1157348 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.9113. Min Act: -0.0000

Data Index: 1688922 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.0379. Min Act: -0.0000

Data Index: 1951519 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.5211. Min Act: -0.0000

Data Index: 205536 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 8.9113. Min Range: -8.9113

Max Act: 7.9130. Min Act: -0.0000

Data Index: 842680 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 8.9113. Min Range: -8.9113

Max Act: 7.9692. Min Act: -0.0000

Data Index: 1105833 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.1207. Min Act: -0.0000

Data Index: 552465 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.0608. Min Act: -0.0000

Data Index: 1967187 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 8.9113. Min Range: -8.9113

Max Act: 7.8240. Min Act: -0.0000

Data Index: 227728 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 8.9113. Min Range: -8.9113

Max Act: 7.5373. Min Act: -0.0000

Data Index: 1640313 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 8.9113. Min Range: -8.9113

Max Act: 7.9330. Min Act: -0.0000

Data Index: 694871 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 8.9113. Min Range: -8.9113

Max Act: 7.3452. Min Act: 0.0000

Data Index: 1210499 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.5078. Min Act: -0.0000

Data Index: 1123640 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 8.9113. Min Range: -8.9113

Max Act: 8.0128. Min Act: -0.0000

Data Index: 65223 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 8.9113. Min Range: -8.9113

Max Act: 7.1454. Min Act: -0.0000

Data Index: 401179 (The Pile)

Max Activating Token Index: 340