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

Dataset: The Pile

Neuron 4752 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: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: 0.0001

Data Index: 199113 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0299. Min Act: 0.0000

Data Index: 189778 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1195271 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0286. Min Act: -0.0000

Data Index: 25601 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0282. Min Act: 0.0001

Data Index: 1185055 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0278. Min Act: -0.0000

Data Index: 196140 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0278. Min Act: -0.0000

Data Index: 292310 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0277. Min Act: -0.0000

Data Index: 550742 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0277. Min Act: -0.0000

Data Index: 938329 (The Pile)

Max Activating Token Index: 5

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0275. Min Act: -0.0000

Data Index: 444979 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0273. Min Act: -0.0000

Data Index: 1614257 (The Pile)

Max Activating Token Index: 2

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0272. Min Act: -0.0000

Data Index: 935404 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0261. Min Act: -0.0000

Data Index: 203611 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0267. Min Act: 0.0000

Data Index: 1411620 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0264. Min Act: 0.0000

Data Index: 1878808 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1884175 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1104821 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0258. Min Act: -0.0000

Data Index: 65571 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0253. Min Act: 0.0000

Data Index: 309143 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0254. Min Act: -0.0000

Data Index: 809846 (The Pile)

Max Activating Token Index: 25