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

Dataset: The Pile

Neuron 2233 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: 1.6016. Min Range: -1.6016

Max Act: 1.6016. Min Act: -0.0000

Data Index: 444003 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3709. Min Act: -0.0000

Data Index: 721124 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.4697. Min Act: -0.0000

Data Index: 1664480 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2780. Min Act: -0.0000

Data Index: 269969 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1998616 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1211. Min Act: -0.0000

Data Index: 724572 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1767414 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1654220 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1305568 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1763968 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1842570 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9001. Min Act: -0.0000

Data Index: 317050 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9728. Min Act: -0.0000

Data Index: 18090 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9381. Min Act: -0.0000

Data Index: 967732 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8899. Min Act: -0.0000

Data Index: 272489 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1923420 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9840. Min Act: -0.0000

Data Index: 756223 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1649992 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.0226. Min Act: -0.0000

Data Index: 762975 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1847883 (The Pile)

Max Activating Token Index: 441