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

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

Neuron 380 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0081. Min Act: -0.0003

Data Index: 7373 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1214929 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1654214 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1258513 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0088. Min Act: -0.0002

Data Index: 312375 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1417772 (Python Code)

Max Activating Token Index: 651

Text #6

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0072. Min Act: -0.0003

Data Index: 114355 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1411855 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1465058 (Python Code)

Max Activating Token Index: 568

Text #9

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1607171 (Python Code)

Max Activating Token Index: 554

Text #10

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1448152 (Python Code)

Max Activating Token Index: 682

Text #11

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0077. Min Act: -0.0003

Data Index: 328873 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0067. Min Act: -0.0003

Data Index: 491189 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1537865 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1467492 (Python Code)

Max Activating Token Index: 690

Text #15

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0076. Min Act: -0.0003

Data Index: 452736 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1592004 (Python Code)

Max Activating Token Index: 525

Text #17

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1584673 (Python Code)

Max Activating Token Index: 540

Text #18

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1280595 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1537036 (Python Code)

Max Activating Token Index: 759