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

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

Neuron 1667 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0006

Data Index: 233109 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0006

Data Index: 181809 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0066. Min Act: -0.0006

Data Index: 824817 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0006

Data Index: 882882 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0006

Data Index: 446786 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0006

Data Index: 749829 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1119611 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1071319 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0006

Data Index: 448593 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1016521 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0006

Data Index: 330343 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0054. Min Act: -0.0006

Data Index: 606543 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0063. Min Act: -0.0006

Data Index: 983386 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0006

Data Index: 501578 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1329420 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0006

Data Index: 156872 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0006

Data Index: 982869 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0006

Data Index: 474316 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1188016 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0006

Data Index: 262243 (C4 (Web Text))

Max Activating Token Index: 374