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

Dataset: The Pile

Neuron 3172 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: 5.9008. Min Range: -5.9008

Max Act: 5.9008. Min Act: -0.0000

Data Index: 650472 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 5.9008. Min Range: -5.9008

Max Act: 5.3370. Min Act: -0.0000

Data Index: 960001 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 5.9008. Min Range: -5.9008

Max Act: 5.2988. Min Act: -0.0000

Data Index: 632937 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 5.9008. Min Range: -5.9008

Max Act: 5.5054. Min Act: -0.0000

Data Index: 189678 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.8082. Min Act: -0.0000

Data Index: 1262438 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.9654. Min Act: -0.0000

Data Index: 569934 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.9333. Min Act: -0.0000

Data Index: 1185325 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.6317. Min Act: -0.0000

Data Index: 1638846 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.2698. Min Act: -0.0000

Data Index: 161985 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.1983. Min Act: -0.0000

Data Index: 583723 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.1028. Min Act: -0.0000

Data Index: 1011110 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.4174. Min Act: -0.0000

Data Index: 1296822 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 5.9008. Min Range: -5.9008

Max Act: 3.9088. Min Act: -0.0000

Data Index: 419347 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.0791. Min Act: -0.0000

Data Index: 208115 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 5.9008. Min Range: -5.9008

Max Act: 3.8534. Min Act: -0.0000

Data Index: 1844090 (The Pile)

Max Activating Token Index: 566

Text #15

Max Range: 5.9008. Min Range: -5.9008

Max Act: 4.1841. Min Act: -0.0000

Data Index: 1758893 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 5.9008. Min Range: -5.9008

Max Act: 3.6546. Min Act: -0.0000

Data Index: 138861 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 5.9008. Min Range: -5.9008

Max Act: 3.6729. Min Act: -0.0000

Data Index: 1578476 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 5.9008. Min Range: -5.9008

Max Act: 3.6044. Min Act: -0.0000

Data Index: 709570 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 5.9008. Min Range: -5.9008

Max Act: 3.5923. Min Act: -0.0000

Data Index: 1878084 (The Pile)

Max Activating Token Index: 977