Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1325 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0139. Min Act: -0.0006

Data Index: 640876 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0130. Min Act: -0.0006

Data Index: 424786 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1304683 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0132. Min Act: -0.0006

Data Index: 76405 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0121. Min Act: -0.0006

Data Index: 59452 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1136052 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0116. Min Act: -0.0006

Data Index: 651597 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0116. Min Act: -0.0006

Data Index: 751256 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0121. Min Act: -0.0006

Data Index: 762148 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1574610 (Python Code)

Max Activating Token Index: 970

Text #10

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0114. Min Act: -0.0006

Data Index: 224798 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0113. Min Act: -0.0006

Data Index: 221021 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1102642 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1313197 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0120. Min Act: -0.0006

Data Index: 476886 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0111. Min Act: -0.0006

Data Index: 93837 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0113. Min Act: -0.0006

Data Index: 521016 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0115. Min Act: -0.0006

Data Index: 381539 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1320206 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.0139. Min Range: -0.0139

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1428851 (Python Code)

Max Activating Token Index: 885