Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 77 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1041978 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0003

Data Index: 426322 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0083. Min Act: -0.0003

Data Index: 918483 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0082. Min Act: -0.0003

Data Index: 309906 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0089. Min Act: -0.0003

Data Index: 771788 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0089. Min Act: -0.0003

Data Index: 442431 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0090. Min Act: -0.0003

Data Index: 209800 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0088. Min Act: -0.0003

Data Index: 833511 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0075. Min Act: -0.0004

Data Index: 1041756 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0080. Min Act: -0.0003

Data Index: 277512 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0086. Min Act: -0.0003

Data Index: 60871 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0003

Data Index: 568595 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0080. Min Act: -0.0003

Data Index: 882191 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0083. Min Act: -0.0003

Data Index: 876263 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0003

Data Index: 680351 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0078. Min Act: -0.0003

Data Index: 878208 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1348875 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0074. Min Act: -0.0003

Data Index: 343853 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1254880 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0081. Min Act: -0.0003

Data Index: 895899 (C4 (Web Text))

Max Activating Token Index: 380