Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 847 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.5172. Min Act: -0.1700

Data Index: 1441372 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.3550. Min Act: -0.1700

Data Index: 1526794 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.3000. Min Act: -0.1700

Data Index: 687456 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.2989. Min Act: -0.1700

Data Index: 1609323 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.3001. Min Act: -0.1700

Data Index: 1548188 (Python Code)

Max Activating Token Index: 893

Text #5

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.2578. Min Act: -0.1700

Data Index: 1385897 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.2626. Min Act: -0.1700

Data Index: 1509812 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.2298. Min Act: -0.1700

Data Index: 1604609 (Python Code)

Max Activating Token Index: 544

Text #8

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.2109. Min Act: -0.1700

Data Index: 1592916 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.2148. Min Act: -0.1700

Data Index: 1514228 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1896. Min Act: -0.1700

Data Index: 1438662 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1813. Min Act: -0.1700

Data Index: 1420656 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.2039. Min Act: -0.1700

Data Index: 1569824 (Python Code)

Max Activating Token Index: 764

Text #13

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1500. Min Act: -0.1700

Data Index: 295470 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1450. Min Act: -0.1700

Data Index: 1404753 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1397. Min Act: -0.1700

Data Index: 1496823 (Python Code)

Max Activating Token Index: 454

Text #16

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1438. Min Act: -0.1700

Data Index: 882445 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1281. Min Act: -0.1700

Data Index: 1466840 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1250. Min Act: -0.1700

Data Index: 1574198 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1432. Min Act: -0.1700

Data Index: 1607196 (Python Code)

Max Activating Token Index: 298