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

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

Neuron 1713 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: 1.8741. Min Range: -1.8741

Max Act: 1.8688. Min Act: -0.0000

Data Index: 1551495 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8741. Min Act: -0.0000

Data Index: 1619348 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.7579. Min Act: -0.0000

Data Index: 1405822 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8399. Min Act: -0.0000

Data Index: 1597103 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1376334 (Python Code)

Max Activating Token Index: 965

Text #5

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.6055. Min Act: -0.0000

Data Index: 1461078 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.6717. Min Act: -0.0000

Data Index: 1380999 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.6222. Min Act: -0.0000

Data Index: 1398533 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.5091. Min Act: -0.0000

Data Index: 1417725 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1575345 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.5658. Min Act: -0.0000

Data Index: 1652186 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1523709 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1498096 (Python Code)

Max Activating Token Index: 231

Text #13

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.5470. Min Act: -0.0000

Data Index: 1501471 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.5947. Min Act: -0.0000

Data Index: 1570230 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.5003. Min Act: -0.0000

Data Index: 1517145 (Python Code)

Max Activating Token Index: 206

Text #16

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.4929. Min Act: -0.0000

Data Index: 1484571 (Python Code)

Max Activating Token Index: 903

Text #17

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.5795. Min Act: -0.0000

Data Index: 1629847 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1414913 (Python Code)

Max Activating Token Index: 402

Text #19

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1424958 (Python Code)

Max Activating Token Index: 1022