Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 25 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.4747. Min Act: -0.1700
Data Index: 1461163 (Python Code)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.3653. Min Act: -0.1700
Data Index: 1639742 (Python Code)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1778. Min Act: -0.1700
Data Index: 1624378 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.2716. Min Act: -0.1700
Data Index: 1425603 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.2872. Min Act: -0.1700
Data Index: 1462736 (Python Code)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1935. Min Act: -0.1700
Data Index: 1540939 (Python Code)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.2247. Min Act: -0.1700
Data Index: 1384724 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1778. Min Act: -0.1700
Data Index: 1378258 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1935. Min Act: -0.1700
Data Index: 1485147 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1310. Min Act: -0.1700
Data Index: 1635887 (Python Code)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.0685. Min Act: -0.1700
Data Index: 1644469 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1622. Min Act: -0.1700
Data Index: 1494735 (Python Code)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1310. Min Act: -0.1700
Data Index: 1411278 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1622. Min Act: -0.1700
Data Index: 1644784 (Python Code)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.0997. Min Act: -0.1700
Data Index: 1432105 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.0997. Min Act: -0.1700
Data Index: 1435199 (Python Code)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1778. Min Act: -0.1700
Data Index: 1391189 (Python Code)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.0528. Min Act: -0.1700
Data Index: 1456874 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.1153. Min Act: -0.1700
Data Index: 1604956 (Python Code)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4747. Min Range: -6.4747
Max Act: 6.0841. Min Act: -0.1700
Data Index: 1588570 (Python Code)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19