Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2549 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.3446. Min Act: -0.1700
Data Index: 8109895 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.3446. Min Act: -0.1700
Data Index: 3336793 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.2821. Min Act: -0.1700
Data Index: 8109893 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.2821. Min Act: -0.1700
Data Index: 2684118 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.2821. Min Act: -0.1700
Data Index: 2911846 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.2821. Min Act: -0.1700
Data Index: 7704042 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.2821. Min Act: -0.1700
Data Index: 7644183 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.1571. Min Act: -0.1700
Data Index: 4543203 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.1571. Min Act: -0.1700
Data Index: 2939106 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.1571. Min Act: -0.1700
Data Index: 706036 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0946. Min Act: -0.1700
Data Index: 3218779 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0946. Min Act: -0.1700
Data Index: 1270843 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0946. Min Act: -0.1700
Data Index: 5021557 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0946. Min Act: -0.1700
Data Index: 4664942 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0946. Min Act: -0.1700
Data Index: 2672070 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0321. Min Act: -0.1700
Data Index: 1075093 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0946. Min Act: -0.1700
Data Index: 7234514 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0321. Min Act: -0.1700
Data Index: 34593 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0321. Min Act: -0.1700
Data Index: 6124830 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3446. Min Range: -8.3446
Max Act: 8.0321. Min Act: -0.1700
Data Index: 1016431 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19