Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3365 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4723. Min Range: -10.4723
Max Act: 10.4723. Min Act: -0.1700
Data Index: 6028080 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4723. Min Range: -10.4723
Max Act: 10.3473. Min Act: -0.1700
Data Index: 4363288 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4723. Min Range: -10.4723
Max Act: 10.1598. Min Act: -0.1699
Data Index: 7460628 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4723. Min Range: -10.4723
Max Act: 10.0973. Min Act: -0.1700
Data Index: 6731830 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4723. Min Range: -10.4723
Max Act: 10.0973. Min Act: -0.1700
Data Index: 8315010 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4723. Min Range: -10.4723
Max Act: 10.0348. Min Act: -0.1700
Data Index: 20016 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4723. Min Range: -10.4723
Max Act: 10.0348. Min Act: -0.1700
Data Index: 6012831 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9723. Min Act: -0.1700
Data Index: 2880806 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9723. Min Act: -0.1700
Data Index: 2751077 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9723. Min Act: -0.1700
Data Index: 1740849 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9723. Min Act: -0.1700
Data Index: 5244479 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9723. Min Act: -0.1700
Data Index: 7138578 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9723. Min Act: -0.1700
Data Index: 1218403 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9098. Min Act: -0.1700
Data Index: 4726329 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9098. Min Act: -0.1700
Data Index: 8103191 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.9098. Min Act: -0.1700
Data Index: 8557367 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.7848. Min Act: -0.1699
Data Index: 4490708 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.8473. Min Act: -0.1700
Data Index: 8697258 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.8473. Min Act: -0.1700
Data Index: 8529078 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4723. Min Range: -10.4723
Max Act: 9.8473. Min Act: -0.1700
Data Index: 2751084 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19