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

Dataset: The Pile

Neuron 1034 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: 0.5440. Min Range: -0.5440

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1481893 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1487594 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5001. Min Act: -0.0000

Data Index: 619018 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5130. Min Act: -0.0000

Data Index: 34390 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1901014 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1435037 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5028. Min Act: -0.0000

Data Index: 618228 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1023286 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1242784 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4690. Min Act: -0.0000

Data Index: 461363 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1880685 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1277127 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4660. Min Act: 0.0000

Data Index: 1118979 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1353224 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1385237 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4220. Min Act: -0.0000

Data Index: 166533 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1328482 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4576. Min Act: 0.0000

Data Index: 1158487 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.3877. Min Act: -0.0000

Data Index: 411026 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1640847 (The Pile)

Max Activating Token Index: 1010