Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1867 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1468673 (Python Code)

Max Activating Token Index: 789

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0005

Data Index: 636495 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1622930 (Python Code)

Max Activating Token Index: 184

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1523375 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0005

Data Index: 504444 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1415405 (Python Code)

Max Activating Token Index: 783

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1407131 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 720174 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 999429 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1410989 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1486621 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 712026 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1483734 (Python Code)

Max Activating Token Index: 171

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1483653 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0005

Data Index: 799519 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1448877 (Python Code)

Max Activating Token Index: 197

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1554054 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1216962 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1476428 (Python Code)

Max Activating Token Index: 371

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1458883 (Python Code)

Max Activating Token Index: 583