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

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

Neuron 5796 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: 0.1410. Min Range: -0.1410

Max Act: 0.1410. Min Act: -0.0002

Data Index: 1461094 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1380885 (Python Code)

Max Activating Token Index: 83

Text #2

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1535139 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1562752 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1447639 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1554282 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1610357 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1462142 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1649367 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1465470 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1395655 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1474348 (Python Code)

Max Activating Token Index: 360

Text #12

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1597369 (Python Code)

Max Activating Token Index: 215

Text #13

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1629820 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1537515 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1487542 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1510682 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1533729 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1499340 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1652249 (Python Code)

Max Activating Token Index: 54