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

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

Neuron 3065 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0004

Data Index: 1077177 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0004

Data Index: 1311399 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0152. Min Act: -0.0004

Data Index: 813450 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0152. Min Act: -0.0004

Data Index: 567703 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0004

Data Index: 133654 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0134. Min Act: -0.0004

Data Index: 563823 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0145. Min Act: -0.0004

Data Index: 99847 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0142. Min Act: -0.0004

Data Index: 1225792 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0151. Min Act: -0.0004

Data Index: 716360 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0132. Min Act: -0.0004

Data Index: 162714 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0097. Min Act: -0.0004

Data Index: 203982 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1159333 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0120. Min Act: -0.0004

Data Index: 239339 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0137. Min Act: -0.0004

Data Index: 1158177 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0132. Min Act: -0.0004

Data Index: 137015 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0122. Min Act: -0.0004

Data Index: 641409 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0135. Min Act: -0.0004

Data Index: 858229 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0124. Min Act: -0.0004

Data Index: 695778 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0119. Min Act: -0.0004

Data Index: 5590 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0125. Min Act: -0.0004

Data Index: 988711 (C4 (Web Text))

Max Activating Token Index: 734