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

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

Neuron 912 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: 0.0094. Min Range: -0.0094

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1245265 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0089. Min Act: -0.0004

Data Index: 816867 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0086. Min Act: -0.0003

Data Index: 409884 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1287442 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1615823 (Python Code)

Max Activating Token Index: 944

Text #5

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0081. Min Act: -0.0003

Data Index: 42926 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1118834 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1416313 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0073. Min Act: -0.0003

Data Index: 532746 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0074. Min Act: -0.0003

Data Index: 804837 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1401414 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1551113 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1187824 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0069. Min Act: -0.0003

Data Index: 326102 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1601206 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1447191 (Python Code)

Max Activating Token Index: 598

Text #16

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0068. Min Act: -0.0003

Data Index: 563530 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0067. Min Act: -0.0003

Data Index: 48146 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0067. Min Act: -0.0004

Data Index: 211993 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0067. Min Act: -0.0003

Data Index: 670535 (C4 (Web Text))

Max Activating Token Index: 651