Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.9098. Min Act: -0.1700
Data Index: 2759736 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.8473. Min Act: -0.1700
Data Index: 7987240 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.8473. Min Act: -0.1700
Data Index: 5701039 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.7848. Min Act: -0.1700
Data Index: 5424254 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.7848. Min Act: -0.1700
Data Index: 786547 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.7848. Min Act: -0.1700
Data Index: 7055312 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.6598. Min Act: -0.1700
Data Index: 7416026 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.6598. Min Act: -0.1700
Data Index: 8085659 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.6598. Min Act: -0.1700
Data Index: 5528556 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.6598. Min Act: -0.1700
Data Index: 2665279 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5348. Min Act: -0.1700
Data Index: 7351297 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5973. Min Act: -0.1700
Data Index: 7320174 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5973. Min Act: -0.1700
Data Index: 4431124 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5973. Min Act: -0.1700
Data Index: 4094279 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5973. Min Act: -0.1700
Data Index: 3192545 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5973. Min Act: -0.1700
Data Index: 6981448 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5348. Min Act: -0.1700
Data Index: 3698654 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5348. Min Act: -0.1700
Data Index: 1475273 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5348. Min Act: -0.1700
Data Index: 1049412 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9098. Min Range: -8.9098
Max Act: 8.5348. Min Act: -0.1700
Data Index: 6604026 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19