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

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

Neuron 240 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: 0.0087. Min Range: -0.0087

Max Act: 0.0086. Min Act: -0.0006

Data Index: 156291 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0087. Min Act: -0.0006

Data Index: 328593 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1319033 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0080. Min Act: -0.0006

Data Index: 725819 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1102291 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1024079 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0082. Min Act: -0.0006

Data Index: 264603 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0079. Min Act: -0.0006

Data Index: 360247 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0079. Min Act: -0.0006

Data Index: 426900 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0078. Min Act: -0.0006

Data Index: 408532 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0078. Min Act: -0.0006

Data Index: 76670 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0078. Min Act: -0.0006

Data Index: 391530 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1246925 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1295310 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0076. Min Act: -0.0006

Data Index: 641943 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1167611 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1271699 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 154705 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 67925 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0075. Min Act: -0.0006

Data Index: 81650 (C4 (Web Text))

Max Activating Token Index: 409