Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 186 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1691. Min Range: -5.1691
Max Act: 5.1691. Min Act: -0.1700
Data Index: 634956 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1691. Min Range: -5.1691
Max Act: 5.0129. Min Act: -0.1700
Data Index: 175848 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.9504. Min Act: -0.1700
Data Index: 1075479 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.8879. Min Act: -0.1700
Data Index: 1491141 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.8566. Min Act: -0.1700
Data Index: 1003143 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.8254. Min Act: -0.1700
Data Index: 1248974 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7629. Min Act: -0.1700
Data Index: 409657 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7004. Min Act: -0.1700
Data Index: 1489237 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7629. Min Act: -0.1700
Data Index: 1610837 (Python Code)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7629. Min Act: -0.1700
Data Index: 78532 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7316. Min Act: -0.1700
Data Index: 1133132 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.8254. Min Act: -0.1700
Data Index: 62758 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7629. Min Act: -0.1699
Data Index: 1212788 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7316. Min Act: -0.1700
Data Index: 1507967 (Python Code)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7941. Min Act: -0.1700
Data Index: 1635117 (Python Code)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7629. Min Act: -0.1700
Data Index: 1191830 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7629. Min Act: -0.1700
Data Index: 1362108 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7629. Min Act: -0.1700
Data Index: 619591 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7316. Min Act: -0.1700
Data Index: 873773 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1691. Min Range: -5.1691
Max Act: 4.7004. Min Act: -0.1700
Data Index: 675959 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19