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

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

Neuron 1403 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: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 598495 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1443275 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1464003 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1372552 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1364105 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1488676 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1453180 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1485824 (Python Code)

Max Activating Token Index: 700

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1540036 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 38584 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1592555 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1372239 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1606450 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0003

Data Index: 393319 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1240929 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0004

Data Index: 780462 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1636866 (Python Code)

Max Activating Token Index: 838

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 22896 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0004

Data Index: 479593 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1471920 (Python Code)

Max Activating Token Index: 342