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

Dataset: The Pile

Neuron 4453 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: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0000

Data Index: 349722 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1297071 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0268. Min Act: -0.0000

Data Index: 475658 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0263. Min Act: -0.0000

Data Index: 591161 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0272. Min Act: -0.0000

Data Index: 229023 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0261. Min Act: -0.0000

Data Index: 1347545 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1660675 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1467726 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0255. Min Act: -0.0000

Data Index: 1045409 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0248. Min Act: -0.0000

Data Index: 611949 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0248. Min Act: -0.0000

Data Index: 651814 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1341473 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0251. Min Act: -0.0000

Data Index: 454860 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0249. Min Act: -0.0000

Data Index: 1332734 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0239. Min Act: -0.0000

Data Index: 964864 (The Pile)

Max Activating Token Index: 2

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0228. Min Act: -0.0000

Data Index: 654827 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0234. Min Act: -0.0000

Data Index: 497457 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1941704 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1065689 (The Pile)

Max Activating Token Index: 2

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0234. Min Act: -0.0000

Data Index: 511248 (The Pile)

Max Activating Token Index: 16