Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 25 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.1711. Min Act: -0.1700
Data Index: 1558318 (Python Code)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.0608. Min Act: -0.1700
Data Index: 1414778 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.0766. Min Act: -0.1700
Data Index: 1560906 (Python Code)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.0450. Min Act: -0.1700
Data Index: 1574338 (Python Code)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.0134. Min Act: -0.1700
Data Index: 1560904 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.0134. Min Act: -0.1700
Data Index: 1488449 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.0134. Min Act: -0.1700
Data Index: 1429593 (Python Code)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1711. Min Range: -3.1711
Max Act: 3.0134. Min Act: -0.1700
Data Index: 1453559 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9818. Min Act: -0.1700
Data Index: 1627741 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9818. Min Act: -0.1700
Data Index: 1593186 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9976. Min Act: -0.1700
Data Index: 1563331 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9818. Min Act: -0.1700
Data Index: 1551350 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9818. Min Act: -0.1700
Data Index: 1374819 (Python Code)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9501. Min Act: -0.1700
Data Index: 1631604 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9660. Min Act: -0.1700
Data Index: 1467933 (Python Code)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9660. Min Act: -0.1700
Data Index: 1457078 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9501. Min Act: -0.1700
Data Index: 1615426 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9660. Min Act: -0.1700
Data Index: 1457285 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9343. Min Act: -0.1700
Data Index: 1596596 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1711. Min Range: -3.1711
Max Act: 2.9343. Min Act: -0.1700
Data Index: 1376190 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19