Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1109 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1152791 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0003

Data Index: 373153 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0003

Data Index: 78404 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1559717 (Python Code)

Max Activating Token Index: 824

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1174186 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 613656 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1629127 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1467083 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0003

Data Index: 641887 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1651447 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1437125 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0004

Data Index: 1111692 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0004

Data Index: 780321 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0003

Data Index: 75315 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1554527 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1506859 (Python Code)

Max Activating Token Index: 976

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0003

Data Index: 469804 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0003

Data Index: 778973 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1400884 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0004

Data Index: 1035328 (C4 (Web Text))

Max Activating Token Index: 927