Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1643 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1498777 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1485625 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1638988 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0083. Min Act: -0.0003

Data Index: 548570 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1461297 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1394800 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1475447 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1038790 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1599303 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1642710 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1463048 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1492357 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1464537 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1530772 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1605203 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1568105 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0079. Min Act: -0.0003

Data Index: 580193 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1536508 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1586652 (Python Code)

Max Activating Token Index: 68

Text #19

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1598908 (Python Code)

Max Activating Token Index: 126