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

Dataset: The Pile

Neuron 3638 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.6047. Min Act: -0.0000

Data Index: 435828 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.6010. Min Act: -0.0000

Data Index: 199153 (The Pile)

Max Activating Token Index: 777

Text #2

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.6000. Min Act: -0.0000

Data Index: 873393 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1630850 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1956339 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5496. Min Act: -0.0000

Data Index: 911460 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1655304 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1253317 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4641. Min Act: -0.0000

Data Index: 602777 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1935446 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1974287 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1595885 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1955665 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4750. Min Act: -0.0000

Data Index: 787458 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1589441 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1658250 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1223686 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1721523 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1141410 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1820307 (The Pile)

Max Activating Token Index: 826