Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 512 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.5250. Min Act: -0.0003

Data Index: 1368412 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2840. Min Act: -0.0004

Data Index: 1520298 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.3362. Min Act: -0.0004

Data Index: 1378297 (Python Code)

Max Activating Token Index: 762

Text #3

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.0732. Min Act: -0.0004

Data Index: 1380046 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.9753. Min Act: -0.0004

Data Index: 1598623 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.9210. Min Act: -0.0004

Data Index: 1362968 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.8988. Min Act: -0.0004

Data Index: 1296984 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.8929. Min Act: -0.0004

Data Index: 1434715 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.8092. Min Act: -0.0004

Data Index: 1437924 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6731. Min Act: -0.0004

Data Index: 1626598 (Python Code)

Max Activating Token Index: 664

Text #10

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6883. Min Act: -0.0004

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6792. Min Act: -0.0004

Data Index: 1375545 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6620. Min Act: -0.0003

Data Index: 1469663 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6331. Min Act: -0.0004

Data Index: 1560403 (Python Code)

Max Activating Token Index: 976

Text #14

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6365. Min Act: -0.0004

Data Index: 1561897 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6510. Min Act: -0.0004

Data Index: 1456189 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6173. Min Act: -0.0004

Data Index: 1417047 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6189. Min Act: -0.0004

Data Index: 1512986 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.6001. Min Act: -0.0004

Data Index: 1580556 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 1.5250. Min Range: -1.5250

Max Act: 0.5939. Min Act: -0.0004

Data Index: 1499970 (Python Code)

Max Activating Token Index: 713