Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0528. Min Range: -5.0528
Max Act: 5.0528. Min Act: -0.1700
Data Index: 8375987 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.9278. Min Act: -0.1700
Data Index: 1646315 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.8340. Min Act: -0.1700
Data Index: 7370251 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.8340. Min Act: -0.1700
Data Index: 4941806 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.8028. Min Act: -0.1700
Data Index: 1768699 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.8028. Min Act: -0.1700
Data Index: 7550621 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7403. Min Act: -0.1700
Data Index: 3908013 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7715. Min Act: -0.1700
Data Index: 7137955 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7715. Min Act: -0.1700
Data Index: 3722930 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7715. Min Act: -0.1700
Data Index: 4984015 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7403. Min Act: -0.1700
Data Index: 5922300 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7090. Min Act: -0.1700
Data Index: 8419030 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7090. Min Act: -0.1700
Data Index: 129315 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7090. Min Act: -0.1700
Data Index: 7018214 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7090. Min Act: -0.1700
Data Index: 4984020 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.6778. Min Act: -0.1700
Data Index: 8807735 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.7090. Min Act: -0.1700
Data Index: 5866450 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.6778. Min Act: -0.1700
Data Index: 8226067 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.6778. Min Act: -0.1700
Data Index: 828999 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0528. Min Range: -5.0528
Max Act: 4.6778. Min Act: -0.1700
Data Index: 4167743 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19