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

Dataset: The Pile

Neuron 4559 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: 0.7991. Min Range: -0.7991

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1889117 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7561. Min Act: -0.0000

Data Index: 546298 (The Pile)

Max Activating Token Index: 811

Text #2

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7504. Min Act: -0.0000

Data Index: 792955 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7758. Min Act: 0.0000

Data Index: 887828 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1920387 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1181541 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6535. Min Act: -0.0000

Data Index: 338223 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6422. Min Act: -0.0000

Data Index: 593017 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1236149 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6229. Min Act: -0.0000

Data Index: 618132 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1468229 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6130. Min Act: 0.0000

Data Index: 492656 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6100. Min Act: 0.0000

Data Index: 1603374 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1577946 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5816. Min Act: -0.0000

Data Index: 495930 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6020. Min Act: -0.0000

Data Index: 403463 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1342169 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5848. Min Act: -0.0000

Data Index: 311331 (The Pile)

Max Activating Token Index: 764

Text #18

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1822399 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5637. Min Act: 0.0000

Data Index: 833524 (The Pile)

Max Activating Token Index: 653