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

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

Neuron 516 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: 0.0083. Min Range: -0.0083

Max Act: 0.0081. Min Act: -0.0005

Data Index: 1404229 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0005

Data Index: 740895 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0080. Min Act: -0.0005

Data Index: 1427055 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0005

Data Index: 915651 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1379354 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0005

Data Index: 479548 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0005

Data Index: 356352 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0005

Data Index: 1507981 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0005

Data Index: 867111 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1517908 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1488072 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1632040 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1178305 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1420787 (Python Code)

Max Activating Token Index: 657

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1428160 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0068. Min Act: -0.0005

Data Index: 1185950 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1396107 (Python Code)

Max Activating Token Index: 343

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0068. Min Act: -0.0005

Data Index: 1578220 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0068. Min Act: -0.0005

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0068. Min Act: -0.0005

Data Index: 31067 (C4 (Web Text))

Max Activating Token Index: 839