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

Dataset: The Pile

Neuron 2521 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: 0.7193. Min Range: -0.7193

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1549274 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5941. Min Act: -0.0000

Data Index: 586843 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1598086 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1386083 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5949. Min Act: -0.0000

Data Index: 29746 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1103575 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1004137 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5279. Min Act: -0.0000

Data Index: 176472 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5203. Min Act: -0.0000

Data Index: 980523 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5318. Min Act: -0.0000

Data Index: 719792 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1931300 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5083. Min Act: -0.0000

Data Index: 278699 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1862641 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1121371 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4229. Min Act: -0.0000

Data Index: 524867 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4181. Min Act: -0.0000

Data Index: 105729 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4201. Min Act: -0.0000

Data Index: 395022 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1968685 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4365. Min Act: -0.0000

Data Index: 9965 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.3877. Min Act: -0.0000

Data Index: 131584 (The Pile)

Max Activating Token Index: 410