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

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

Neuron 1252 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: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0006

Data Index: 218860 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0006

Data Index: 110117 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0006

Data Index: 923633 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0096. Min Act: -0.0006

Data Index: 616328 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0100. Min Act: -0.0006

Data Index: 338666 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0005

Data Index: 1494325 (Python Code)

Max Activating Token Index: 635

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1128212 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0097. Min Act: -0.0005

Data Index: 1363599 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1136886 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0006

Data Index: 74643 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1424351 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0006

Data Index: 137384 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0006

Data Index: 198333 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1098480 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1077286 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0006

Data Index: 611057 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1449457 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0096. Min Act: -0.0006

Data Index: 375442 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0090. Min Act: -0.0005

Data Index: 1443074 (Python Code)

Max Activating Token Index: 905

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0090. Min Act: -0.0006

Data Index: 979980 (C4 (Web Text))

Max Activating Token Index: 932