Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3701 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1564215 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1189. Min Act: -0.0002

Data Index: 1089868 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1468664 (Python Code)

Max Activating Token Index: 854

Text #3

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1142. Min Act: -0.0002

Data Index: 587367 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1156. Min Act: -0.0002

Data Index: 901327 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1169. Min Act: -0.0002

Data Index: 4401 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1121. Min Act: -0.0002

Data Index: 795800 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1108. Min Act: -0.0002

Data Index: 163410 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1126. Min Act: -0.0002

Data Index: 402128 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1094. Min Act: -0.0002

Data Index: 564926 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1032134 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1248393 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1092. Min Act: -0.0002

Data Index: 418028 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1432785 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1063. Min Act: -0.0002

Data Index: 897757 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1092. Min Act: -0.0002

Data Index: 356003 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1423356 (Python Code)

Max Activating Token Index: 587

Text #17

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1580038 (Python Code)

Max Activating Token Index: 911

Text #18

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1052. Min Act: -0.0002

Data Index: 477311 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1077. Min Act: -0.0002

Data Index: 152086 (C4 (Web Text))

Max Activating Token Index: 361