Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1487 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0005

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1557800 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0123. Min Act: -0.0005

Data Index: 367930 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0131. Min Act: -0.0005

Data Index: 701218 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0122. Min Act: -0.0005

Data Index: 766627 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1406584 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0119. Min Act: -0.0005

Data Index: 939558 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0116. Min Act: -0.0005

Data Index: 786058 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0117. Min Act: -0.0005

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0103. Min Act: -0.0005

Data Index: 378951 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1332417 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0105. Min Act: -0.0005

Data Index: 908321 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1521263 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0101. Min Act: -0.0005

Data Index: 1309653 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0104. Min Act: -0.0005

Data Index: 268005 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0100. Min Act: -0.0005

Data Index: 1003683 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1088375 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0106. Min Act: -0.0005

Data Index: 82366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0098. Min Act: -0.0005

Data Index: 1517888 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0101. Min Act: -0.0005

Data Index: 392313 (C4 (Web Text))

Max Activating Token Index: 11