Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 548 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0082. Min Act: -0.0003

Data Index: 685191 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0004

Data Index: 258115 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 188483 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 477644 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 238691 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0004

Data Index: 968486 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 538763 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0004

Data Index: 985596 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0004

Data Index: 523850 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 273338 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0004

Data Index: 845212 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0004

Data Index: 936959 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0003

Data Index: 2040 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0003

Data Index: 526581 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1288827 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 11815 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0004

Data Index: 577308 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0004

Data Index: 75425 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0004

Data Index: 825593 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0004

Data Index: 840377 (C4 (Web Text))

Max Activating Token Index: 319