Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1665 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0004

Data Index: 1476940 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0004

Data Index: 1547853 (Python Code)

Max Activating Token Index: 524

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0074. Min Act: -0.0004

Data Index: 1425344 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1540042 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1363701 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1370457 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0004

Data Index: 900837 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1584004 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1419567 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1647453 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1365384 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1475461 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1460325 (Python Code)

Max Activating Token Index: 202

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1620060 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0004

Data Index: 758349 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0004

Data Index: 370147 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0004

Data Index: 1580293 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0004

Data Index: 41534 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1127287 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1501592 (Python Code)

Max Activating Token Index: 222