Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 787 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1367. Min Act: -0.0000

Data Index: 543580 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1441. Min Act: -0.0000

Data Index: 575530 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1241. Min Act: -0.0000

Data Index: 497113 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1267890 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1168. Min Act: 0.0000

Data Index: 1283815 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1131. Min Act: 0.0000

Data Index: 1072898 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1131. Min Act: 0.0001

Data Index: 939578 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1209. Min Act: -0.0000

Data Index: 767795 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1114. Min Act: -0.0000

Data Index: 386713 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1208. Min Act: -0.0000

Data Index: 254303 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1158418 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1129. Min Act: -0.0000

Data Index: 538733 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1122. Min Act: -0.0000

Data Index: 985763 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1115. Min Act: 0.0000

Data Index: 1634896 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1120. Min Act: -0.0000

Data Index: 660439 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1112. Min Act: -0.0000

Data Index: 222875 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1085. Min Act: 0.0000

Data Index: 269181 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1079. Min Act: -0.0000

Data Index: 176578 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1020013 (C4 (Web Text))

Max Activating Token Index: 106