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

Dataset: The Pile

Neuron 188 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.8846. Min Act: -0.0000

Data Index: 1319400 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.7144. Min Act: -0.0000

Data Index: 1596205 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.6620. Min Act: -0.0000

Data Index: 425936 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.7010. Min Act: -0.0000

Data Index: 1098902 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.4955. Min Act: -0.0000

Data Index: 1255634 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.5634. Min Act: -0.0000

Data Index: 603621 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.5694. Min Act: -0.0000

Data Index: 472608 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1727302 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.6243. Min Act: -0.0000

Data Index: 919893 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1202110 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.5515. Min Act: -0.0000

Data Index: 1927077 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.6753. Min Act: -0.0000

Data Index: 1397326 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.5047. Min Act: -0.0000

Data Index: 1422578 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3953. Min Act: -0.0000

Data Index: 1064071 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.4670. Min Act: -0.0000

Data Index: 252620 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1356889 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1722326 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1868863 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.4286. Min Act: -0.0000

Data Index: 464041 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1140211 (The Pile)

Max Activating Token Index: 495