Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.8163. Min Act: -0.0000

Data Index: 1375167 (Python Code)

Max Activating Token Index: 277

Text #1

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.7458. Min Act: -0.0000

Data Index: 1606888 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.8182. Min Act: -0.0000

Data Index: 1477855 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.6560. Min Act: -0.0000

Data Index: 1510980 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.6585. Min Act: -0.0000

Data Index: 1591454 (Python Code)

Max Activating Token Index: 851

Text #5

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.7757. Min Act: -0.0000

Data Index: 1395097 (Python Code)

Max Activating Token Index: 315

Text #6

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.4973. Min Act: -0.0000

Data Index: 1654297 (Python Code)

Max Activating Token Index: 541

Text #7

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.7575. Min Act: -0.0000

Data Index: 1498389 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.4292. Min Act: -0.0000

Data Index: 1624070 (Python Code)

Max Activating Token Index: 294

Text #9

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.5394. Min Act: -0.0000

Data Index: 1490985 (Python Code)

Max Activating Token Index: 261

Text #10

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.4075. Min Act: -0.0000

Data Index: 1651520 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.5117. Min Act: -0.0000

Data Index: 1633359 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.5124. Min Act: -0.0000

Data Index: 1539912 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.4925. Min Act: -0.0000

Data Index: 1639155 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.6189. Min Act: -0.0000

Data Index: 1561775 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.4609. Min Act: -0.0000

Data Index: 1479963 (Python Code)

Max Activating Token Index: 666

Text #16

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.6167. Min Act: -0.0000

Data Index: 1429716 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.4650. Min Act: -0.0000

Data Index: 1375420 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.4758. Min Act: -0.0000

Data Index: 1463688 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 2.8182. Min Range: -2.8182

Max Act: 2.5906. Min Act: -0.0000

Data Index: 1459579 (Python Code)

Max Activating Token Index: 734