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

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

Neuron 688 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0071. Min Act: -0.0006

Data Index: 970008 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1649620 (Python Code)

Max Activating Token Index: 559

Text #2

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1632671 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0005

Data Index: 1376708 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1514247 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0066. Min Act: -0.0006

Data Index: 381833 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1231406 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1390163 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1637770 (Python Code)

Max Activating Token Index: 1013

Text #9

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1367348 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1638441 (Python Code)

Max Activating Token Index: 545

Text #11

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0005

Data Index: 1423638 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1533118 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1389545 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0006

Data Index: 694859 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1622053 (Python Code)

Max Activating Token Index: 224

Text #16

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1479962 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1638655 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1508009 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1652184 (Python Code)

Max Activating Token Index: 675