Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 852 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0074. Min Act: -0.0004

Data Index: 656997 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0004

Data Index: 897997 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0073. Min Act: -0.0004

Data Index: 572750 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0072. Min Act: -0.0004

Data Index: 503812 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1341826 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0004

Data Index: 1092168 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0004

Data Index: 706173 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0004

Data Index: 66803 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0004

Data Index: 91567 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1126466 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0004

Data Index: 165458 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1584112 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0004

Data Index: 1407500 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0004

Data Index: 124740 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0004

Data Index: 321851 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0004

Data Index: 1216110 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0004

Data Index: 1089899 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0004

Data Index: 894376 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0004

Data Index: 349939 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0004

Data Index: 1501755 (Python Code)

Max Activating Token Index: 538