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

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

Neuron 187 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: 1.9918. Min Range: -1.9918

Max Act: 1.9753. Min Act: -0.0000

Data Index: 1610424 (Python Code)

Max Activating Token Index: 550

Text #1

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.9918. Min Act: -0.0000

Data Index: 1386650 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1587115 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1604100 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.8207. Min Act: -0.0000

Data Index: 1455425 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.7571. Min Act: -0.0000

Data Index: 1089552 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.7717. Min Act: -0.0000

Data Index: 1448678 (Python Code)

Max Activating Token Index: 384

Text #7

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1601626 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.5946. Min Act: -0.0000

Data Index: 576330 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.3495. Min Act: -0.0000

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1092706 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.5566. Min Act: -0.0000

Data Index: 15251 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1474241 (Python Code)

Max Activating Token Index: 768

Text #13

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.4415. Min Act: -0.0000

Data Index: 1292261 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.3974. Min Act: -0.0000

Data Index: 1538320 (Python Code)

Max Activating Token Index: 581

Text #15

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1529441 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1432380 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.4335. Min Act: -0.0000

Data Index: 1399879 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1507538 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 1.9918. Min Range: -1.9918

Max Act: 1.2551. Min Act: -0.0000

Data Index: 1467894 (Python Code)

Max Activating Token Index: 482