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

Dataset: The Pile

Neuron 2013 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1679633 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.1034. Min Act: 0.0000

Data Index: 431458 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0977. Min Act: 0.0000

Data Index: 1597512 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0969. Min Act: -0.0000

Data Index: 561152 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0965. Min Act: 0.0000

Data Index: 1096193 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0959. Min Act: -0.0000

Data Index: 942590 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0956. Min Act: 0.0000

Data Index: 1446473 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0948. Min Act: 0.0000

Data Index: 1467769 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0901. Min Act: 0.0000

Data Index: 1822594 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0929. Min Act: -0.0000

Data Index: 769666 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1068234 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0918. Min Act: -0.0000

Data Index: 241069 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1841552 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0914. Min Act: 0.0000

Data Index: 1100582 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0901. Min Act: -0.0000

Data Index: 472982 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1696855 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0883. Min Act: 0.0000

Data Index: 106231 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0869. Min Act: -0.0000

Data Index: 33550 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0865. Min Act: -0.0000

Data Index: 51786 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1679184 (The Pile)

Max Activating Token Index: 1023