Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.5008. Min Act: -0.1700
Data Index: 4531446 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.4696. Min Act: -0.1700
Data Index: 8803755 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.3446. Min Act: -0.1700
Data Index: 4028608 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.3446. Min Act: -0.1700
Data Index: 6608358 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.3133. Min Act: -0.1700
Data Index: 3621997 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0946. Min Act: -0.1700
Data Index: 650278 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0946. Min Act: -0.1700
Data Index: 2587102 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0321. Min Act: -0.1700
Data Index: 8147049 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0321. Min Act: -0.1700
Data Index: 7933186 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0321. Min Act: -0.1700
Data Index: 5061068 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0321. Min Act: -0.1700
Data Index: 7307983 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0321. Min Act: -0.1700
Data Index: 6874680 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5008. Min Range: -7.5008
Max Act: 6.9696. Min Act: -0.1700
Data Index: 1811006 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5008. Min Range: -7.5008
Max Act: 6.9696. Min Act: -0.1700
Data Index: 641936 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5008. Min Range: -7.5008
Max Act: 7.0008. Min Act: -0.1700
Data Index: 451911 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5008. Min Range: -7.5008
Max Act: 6.9071. Min Act: -0.1700
Data Index: 6598384 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5008. Min Range: -7.5008
Max Act: 6.8446. Min Act: -0.1700
Data Index: 6754369 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5008. Min Range: -7.5008
Max Act: 6.9071. Min Act: -0.1700
Data Index: 7961771 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5008. Min Range: -7.5008
Max Act: 6.8758. Min Act: -0.1700
Data Index: 1618588 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5008. Min Range: -7.5008
Max Act: 6.9071. Min Act: -0.1700
Data Index: 1223953 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19