Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1968 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0000

Data Index: 206772 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1121030 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0279. Min Act: 0.0000

Data Index: 1613013 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0266. Min Act: 0.0000

Data Index: 189086 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0265. Min Act: 0.0000

Data Index: 287750 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1587536 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0262. Min Act: 0.0000

Data Index: 1600587 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0272. Min Act: 0.0000

Data Index: 1808648 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0261. Min Act: 0.0000

Data Index: 79045 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0260. Min Act: 0.0000

Data Index: 167905 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1159276 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0259. Min Act: 0.0000

Data Index: 577978 (The Pile)

Max Activating Token Index: 36

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0255. Min Act: 0.0000

Data Index: 1759676 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0256. Min Act: -0.0000

Data Index: 1120650 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0255. Min Act: 0.0000

Data Index: 872569 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0253. Min Act: -0.0000

Data Index: 1458241 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0253. Min Act: -0.0000

Data Index: 185311 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0250. Min Act: -0.0000

Data Index: 721940 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0250. Min Act: -0.0000

Data Index: 572897 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0249. Min Act: 0.0000

Data Index: 1623301 (The Pile)

Max Activating Token Index: 9