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

Dataset: The Pile

Neuron 1887 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: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0000

Data Index: 713363 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0062. Min Act: -0.0000

Data Index: 709532 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0000

Data Index: 853605 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0030. Min Act: -0.0000

Data Index: 217100 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0018. Min Act: -0.0000

Data Index: 614019 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0023. Min Act: -0.0000

Data Index: 705227 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1065485 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1272856 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0023. Min Act: -0.0001

Data Index: 100207 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0030. Min Act: -0.0001

Data Index: 1787376 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0025. Min Act: -0.0000

Data Index: 1412300 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0023. Min Act: -0.0000

Data Index: 1891615 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0027. Min Act: -0.0001

Data Index: 476293 (The Pile)

Max Activating Token Index: 828

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1025127 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0021. Min Act: -0.0001

Data Index: 1116221 (The Pile)

Max Activating Token Index: 358

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1153293 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0016. Min Act: -0.0000

Data Index: 153027 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0022. Min Act: -0.0000

Data Index: 1938286 (The Pile)

Max Activating Token Index: 620

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0019. Min Act: -0.0000

Data Index: 21644 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0020. Min Act: -0.0001

Data Index: 1321978 (The Pile)

Max Activating Token Index: 220