Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2449 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.3723. Min Act: -0.1700
Data Index: 5589300 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.2161. Min Act: -0.1700
Data Index: 1168252 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.1536. Min Act: -0.1700
Data Index: 5851751 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.0911. Min Act: -0.1700
Data Index: 5021536 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.0598. Min Act: -0.1700
Data Index: 1940552 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.0598. Min Act: -0.1700
Data Index: 3031453 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.0598. Min Act: -0.1700
Data Index: 6079747 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.0286. Min Act: -0.1700
Data Index: 6979294 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3723. Min Range: -6.3723
Max Act: 6.0286. Min Act: -0.1700
Data Index: 2926034 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9973. Min Act: -0.1700
Data Index: 5608664 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9661. Min Act: -0.1700
Data Index: 5851554 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9661. Min Act: -0.1700
Data Index: 2482993 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9661. Min Act: -0.1700
Data Index: 4548733 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9661. Min Act: -0.1700
Data Index: 6449581 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9973. Min Act: -0.1700
Data Index: 829062 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9348. Min Act: -0.1700
Data Index: 8201817 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9661. Min Act: -0.1700
Data Index: 2998940 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9348. Min Act: -0.1700
Data Index: 8534944 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9348. Min Act: -0.1700
Data Index: 275315 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3723. Min Range: -6.3723
Max Act: 5.9036. Min Act: -0.1700
Data Index: 2865722 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19