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

Dataset: The Pile

Neuron 1355 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: 0.1300. Min Range: -0.1300

Max Act: 0.1300. Min Act: -0.0000

Data Index: 618809 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1969581 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1645549 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0961. Min Act: -0.0000

Data Index: 816915 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0835. Min Act: -0.0000

Data Index: 986506 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0867. Min Act: -0.0000

Data Index: 952300 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1378912 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1242946 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1948991 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1170264 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1838732 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0853. Min Act: -0.0000

Data Index: 676100 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0803. Min Act: -0.0000

Data Index: 171794 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1499465 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0889. Min Act: -0.0000

Data Index: 957038 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1837016 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0712. Min Act: -0.0000

Data Index: 837461 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0774. Min Act: -0.0000

Data Index: 41759 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1771047 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1841678 (The Pile)

Max Activating Token Index: 844