Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 133 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.6556. Min Act: -0.1700
Data Index: 1499693 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.6075. Min Act: -0.1700
Data Index: 1217086 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.6075. Min Act: -0.1700
Data Index: 1245531 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5752. Min Act: -0.1700
Data Index: 1119748 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5752. Min Act: -0.1700
Data Index: 301569 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5752. Min Act: -0.1700
Data Index: 1129965 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5591. Min Act: -0.1700
Data Index: 1470950 (Python Code)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5591. Min Act: -0.1700
Data Index: 634247 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5430. Min Act: -0.1700
Data Index: 220885 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4945. Min Act: -0.1700
Data Index: 841558 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5107. Min Act: -0.1700
Data Index: 1357277 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.5107. Min Act: -0.1700
Data Index: 1498494 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4782. Min Act: -0.1700
Data Index: 295002 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4620. Min Act: -0.1700
Data Index: 51518 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4620. Min Act: -0.1700
Data Index: 627927 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4782. Min Act: -0.1700
Data Index: 718285 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4620. Min Act: -0.1700
Data Index: 988417 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4458. Min Act: -0.1700
Data Index: 1074552 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4458. Min Act: -0.1700
Data Index: 130487 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6556. Min Range: -2.6556
Max Act: 2.4620. Min Act: -0.1700
Data Index: 788462 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19