Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.7056. Min Act: -0.0000

Data Index: 840669 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.7276. Min Act: -0.0000

Data Index: 392719 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1071740 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6494. Min Act: -0.0000

Data Index: 713155 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1170566 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6331. Min Act: -0.0000

Data Index: 179500 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6914. Min Act: -0.0000

Data Index: 404391 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1118940 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1120114 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6284. Min Act: -0.0000

Data Index: 35762 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1076573 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5867. Min Act: -0.0000

Data Index: 490444 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1166636 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5985. Min Act: -0.0000

Data Index: 244839 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1325909 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1176641 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5929. Min Act: -0.0000

Data Index: 657964 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1196761 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1212287 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5796. Min Act: -0.0000

Data Index: 664581 (C4 (Web Text))

Max Activating Token Index: 116