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

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

Neuron 4083 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: 0.1201. Min Range: -0.1201

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1625037 (Python Code)

Max Activating Token Index: 547

Text #1

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1378664 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1400457 (Python Code)

Max Activating Token Index: 71

Text #3

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1656866 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1489564 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1124. Min Act: -0.0002

Data Index: 1510165 (Python Code)

Max Activating Token Index: 909

Text #6

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1411445 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1605058 (Python Code)

Max Activating Token Index: 640

Text #8

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1559088 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1602422 (Python Code)

Max Activating Token Index: 713

Text #10

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1428263 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1363856 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1614105 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1454322 (Python Code)

Max Activating Token Index: 279

Text #14

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1577724 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1447356 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1386387 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1457048 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1565737 (Python Code)

Max Activating Token Index: 694

Text #19

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1625290 (Python Code)

Max Activating Token Index: 829