Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1359 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1168962 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1263982 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1371649 (Python Code)

Max Activating Token Index: 378

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0095. Min Act: -0.0002

Data Index: 324991 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1559757 (Python Code)

Max Activating Token Index: 465

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1414307 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1366051 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0089. Min Act: -0.0002

Data Index: 213653 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1503673 (Python Code)

Max Activating Token Index: 393

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1406033 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1422951 (Python Code)

Max Activating Token Index: 484

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1613463 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1591388 (Python Code)

Max Activating Token Index: 814

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1415567 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1564492 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1368654 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0088. Min Act: -0.0002

Data Index: 749500 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1571692 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1626686 (Python Code)

Max Activating Token Index: 314

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1635476 (Python Code)

Max Activating Token Index: 114