Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2714 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1655379 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1301. Min Act: -0.0000

Data Index: 12241 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1812202 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1231. Min Act: -0.0000

Data Index: 148344 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1192. Min Act: -0.0000

Data Index: 486153 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1477424 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1646215 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1081. Min Act: -0.0000

Data Index: 838113 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1246. Min Act: -0.0000

Data Index: 6948 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1666787 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1079. Min Act: -0.0000

Data Index: 661306 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1126660 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1612091 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1564685 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1107. Min Act: -0.0000

Data Index: 921227 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1000. Min Act: -0.0001

Data Index: 589331 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1033. Min Act: -0.0001

Data Index: 808686 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1236140 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.0991. Min Act: -0.0001

Data Index: 582114 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.0957. Min Act: -0.0000

Data Index: 471145 (The Pile)

Max Activating Token Index: 98