Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 587 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0112. Min Act: -0.0005

Data Index: 475921 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1325802 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0114. Min Act: -0.0006

Data Index: 445334 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1130404 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0111. Min Act: -0.0006

Data Index: 155005 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0106. Min Act: -0.0006

Data Index: 978998 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0106. Min Act: -0.0006

Data Index: 478993 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0105. Min Act: -0.0006

Data Index: 273402 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0104. Min Act: -0.0006

Data Index: 414909 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0096. Min Act: -0.0006

Data Index: 486965 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1041395 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0096. Min Act: -0.0006

Data Index: 310065 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1181031 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0094. Min Act: -0.0006

Data Index: 618201 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0099. Min Act: -0.0006

Data Index: 4232 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0099. Min Act: -0.0006

Data Index: 531870 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0095. Min Act: -0.0006

Data Index: 938362 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1232013 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1328531 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1122511 (C4 (Web Text))

Max Activating Token Index: 562