Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1120 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.2747. Min Act: -0.1700
Data Index: 368385 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.2417. Min Act: -0.1700
Data Index: 722035 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.2086. Min Act: -0.1700
Data Index: 1531560 (Python Code)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.2251. Min Act: -0.1700
Data Index: 912798 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1754. Min Act: -0.1700
Data Index: 1392921 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1754. Min Act: -0.1700
Data Index: 1654490 (Python Code)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1588. Min Act: -0.1700
Data Index: 1531622 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1588. Min Act: -0.1700
Data Index: 204708 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1588. Min Act: -0.1700
Data Index: 1397257 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1588. Min Act: -0.1700
Data Index: 1101544 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1421. Min Act: -0.1700
Data Index: 533700 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1421. Min Act: -0.1700
Data Index: 202648 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1421. Min Act: -0.1700
Data Index: 409786 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1254. Min Act: -0.1700
Data Index: 1541153 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1254. Min Act: -0.1700
Data Index: 1369227 (Python Code)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1087. Min Act: -0.1700
Data Index: 1514982 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1087. Min Act: -0.1700
Data Index: 1309713 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1087. Min Act: -0.1700
Data Index: 986297 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1087. Min Act: -0.1700
Data Index: 1566500 (Python Code)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2747. Min Range: -2.2747
Max Act: 2.1087. Min Act: -0.1700
Data Index: 133705 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19