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

Dataset: The Pile

Neuron 1067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5876. Min Act: -0.0000

Data Index: 915265 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1523209 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1348547 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1433978 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1379620 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5302. Min Act: -0.0000

Data Index: 959803 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1699262 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5740. Min Act: -0.0000

Data Index: 205065 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1921199 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1252829 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1873695 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5619. Min Act: -0.0000

Data Index: 919417 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5231. Min Act: -0.0000

Data Index: 551601 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1125318 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4967. Min Act: -0.0000

Data Index: 55895 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5408. Min Act: -0.0000

Data Index: 747800 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5023. Min Act: -0.0000

Data Index: 587681 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5455. Min Act: -0.0000

Data Index: 774638 (The Pile)

Max Activating Token Index: 57

Text #18

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5273. Min Act: -0.0000

Data Index: 66285 (The Pile)

Max Activating Token Index: 401

Text #19

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1216057 (The Pile)

Max Activating Token Index: 719