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

Dataset: The Pile

Neuron 4096 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: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0000

Data Index: 170438 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1147949 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0223. Min Act: -0.0000

Data Index: 1860295 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0221. Min Act: -0.0000

Data Index: 1105426 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0205. Min Act: 0.0000

Data Index: 834479 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0199. Min Act: -0.0000

Data Index: 1942849 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0199. Min Act: -0.0000

Data Index: 1125368 (The Pile)

Max Activating Token Index: 14

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0197. Min Act: -0.0000

Data Index: 1403523 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0196. Min Act: -0.0000

Data Index: 1780955 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0200. Min Act: -0.0000

Data Index: 113636 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: -0.0000

Data Index: 170949 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: 0.0000

Data Index: 777244 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0184. Min Act: -0.0000

Data Index: 326199 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0184. Min Act: -0.0000

Data Index: 547022 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0180. Min Act: -0.0000

Data Index: 1677639 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0179. Min Act: -0.0000

Data Index: 1558037 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0186. Min Act: -0.0000

Data Index: 321984 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0177. Min Act: -0.0000

Data Index: 1436017 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0168. Min Act: -0.0000

Data Index: 1963914 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0173. Min Act: -0.0000

Data Index: 1182389 (The Pile)

Max Activating Token Index: 22