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

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

Neuron 204 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: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1466991 (Python Code)

Max Activating Token Index: 335

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1435151 (Python Code)

Max Activating Token Index: 724

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1459786 (Python Code)

Max Activating Token Index: 292

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1400725 (Python Code)

Max Activating Token Index: 635

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1577932 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1573641 (Python Code)

Max Activating Token Index: 559

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1637534 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1485490 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1177526 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1605670 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1404041 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1380644 (Python Code)

Max Activating Token Index: 834

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1543697 (Python Code)

Max Activating Token Index: 141

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1522775 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1628749 (Python Code)

Max Activating Token Index: 517

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1412429 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1637113 (Python Code)

Max Activating Token Index: 851

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1424016 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1610897 (Python Code)

Max Activating Token Index: 251

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1463292 (Python Code)

Max Activating Token Index: 636