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

Dataset: The Pile

Neuron 4568 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: 0.8650. Min Range: -0.8650

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1894243 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6859. Min Act: -0.0000

Data Index: 986668 (The Pile)

Max Activating Token Index: 445

Text #2

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6477. Min Act: -0.0000

Data Index: 706316 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1895755 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6057. Min Act: -0.0000

Data Index: 737965 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1111869 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6164. Min Act: -0.0000

Data Index: 11611 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1914292 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1406904 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1443771 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5788. Min Act: -0.0000

Data Index: 66644 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1872201 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1744756 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1093487 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1458404 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.4949. Min Act: -0.0000

Data Index: 569449 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5245. Min Act: -0.0000

Data Index: 503826 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5324. Min Act: -0.0000

Data Index: 54062 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5029. Min Act: -0.0000

Data Index: 464637 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1950451 (The Pile)

Max Activating Token Index: 364