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

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

Neuron 3500 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1484070 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1576267 (Python Code)

Max Activating Token Index: 181

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1520892 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0691. Min Act: -0.0002

Data Index: 161304 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1621744 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1414407 (Python Code)

Max Activating Token Index: 838

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1530698 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1395521 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1369336 (Python Code)

Max Activating Token Index: 777

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1359906 (Python Code)

Max Activating Token Index: 535

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0652. Min Act: -0.0002

Data Index: 318243 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1479843 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1434109 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0670. Min Act: -0.0002

Data Index: 521018 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0615. Min Act: -0.0002

Data Index: 565930 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1570180 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1449717 (Python Code)

Max Activating Token Index: 667

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0627. Min Act: -0.0002

Data Index: 129423 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1583980 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1362179 (Python Code)

Max Activating Token Index: 308