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

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

Neuron 2160 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: 0.0083. Min Act: -0.0003

Data Index: 48279 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0082. Min Act: -0.0004

Data Index: 133243 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1066997 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 293823 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 650288 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 45205 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1226288 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 84945 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 748050 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 477560 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 655541 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 288870 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1174128 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1070048 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0003

Data Index: 191411 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0003

Data Index: 27629 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 866791 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 850251 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1150976 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0003

Data Index: 487231 (C4 (Web Text))

Max Activating Token Index: 698