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

Dataset: The Pile

Neuron 1297 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: 0.7215. Min Range: -0.7215

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1885568 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1890159 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5021. Min Act: -0.0000

Data Index: 911271 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1355191 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4682. Min Act: -0.0000

Data Index: 815913 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4001. Min Act: -0.0000

Data Index: 249717 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1084730 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3823. Min Act: -0.0000

Data Index: 186202 (The Pile)

Max Activating Token Index: 761

Text #8

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4201. Min Act: -0.0000

Data Index: 238179 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4489. Min Act: -0.0000

Data Index: 157814 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1915946 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3830. Min Act: -0.0000

Data Index: 995734 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4136. Min Act: -0.0000

Data Index: 785262 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1094443 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1823234 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1290961 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1752331 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1753771 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4038. Min Act: -0.0000

Data Index: 956831 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.3795. Min Act: -0.0000

Data Index: 586729 (The Pile)

Max Activating Token Index: 936