Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.7821. Min Act: -0.1700
Data Index: 5624254 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.7196. Min Act: -0.1700
Data Index: 4499306 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.7196. Min Act: -0.1700
Data Index: 8670629 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.5946. Min Act: -0.1700
Data Index: 1707369 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.5633. Min Act: -0.1700
Data Index: 5411571 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.4696. Min Act: -0.1700
Data Index: 7978881 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.5008. Min Act: -0.1700
Data Index: 526971 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.4696. Min Act: -0.1700
Data Index: 8508895 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.4383. Min Act: -0.1700
Data Index: 4388069 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.4383. Min Act: -0.1700
Data Index: 217575 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3758. Min Act: -0.1700
Data Index: 1976479 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3758. Min Act: -0.1700
Data Index: 4886174 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3758. Min Act: -0.1700
Data Index: 3822552 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3446. Min Act: -0.1700
Data Index: 5440984 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3446. Min Act: -0.1700
Data Index: 2025876 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3446. Min Act: -0.1700
Data Index: 6536747 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3133. Min Act: -0.1700
Data Index: 7244311 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3446. Min Act: -0.1700
Data Index: 7438379 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.3133. Min Act: -0.1700
Data Index: 8145872 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7821. Min Range: -7.7821
Max Act: 7.2821. Min Act: -0.1700
Data Index: 248109 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19