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

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

Neuron 2700 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: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0003

Data Index: 630556 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0106. Min Act: -0.0003

Data Index: 9252 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0097. Min Act: -0.0003

Data Index: 630524 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0085. Min Act: -0.0003

Data Index: 312149 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0087. Min Act: -0.0003

Data Index: 634960 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0086. Min Act: -0.0004

Data Index: 797236 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0083. Min Act: -0.0003

Data Index: 998795 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1222482 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1138660 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0081. Min Act: -0.0004

Data Index: 1227110 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0079. Min Act: -0.0004

Data Index: 443239 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0079. Min Act: -0.0004

Data Index: 703791 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0076. Min Act: -0.0003

Data Index: 732773 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0078. Min Act: -0.0004

Data Index: 924387 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0076. Min Act: -0.0003

Data Index: 755376 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0076. Min Act: -0.0004

Data Index: 1178187 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0076. Min Act: -0.0004

Data Index: 601509 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1352038 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0075. Min Act: -0.0004

Data Index: 486146 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0074. Min Act: -0.0003

Data Index: 921786 (C4 (Web Text))

Max Activating Token Index: 338