Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1061 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0063. Min Act: -0.0006

Data Index: 908366 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1095916 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0006

Data Index: 29808 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0005

Data Index: 881152 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1285620 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1028789 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0006

Data Index: 656182 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1168356 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0005

Data Index: 780220 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: -0.0006

Data Index: 340359 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: -0.0006

Data Index: 336977 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1197373 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0005

Data Index: 621559 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0006

Data Index: 327040 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: -0.0005

Data Index: 296252 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0005

Data Index: 566236 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0005

Data Index: 524845 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: -0.0005

Data Index: 53920 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0049. Min Act: -0.0005

Data Index: 1095979 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1620337 (Python Code)

Max Activating Token Index: 163