Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.9875. Min Act: -0.1700
Data Index: 8585101 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0187. Min Range: -5.0187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 2365459 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.9562. Min Act: -0.1700
Data Index: 4818332 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8625. Min Act: -0.1700
Data Index: 4503335 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8625. Min Act: -0.1700
Data Index: 16002 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8000. Min Act: -0.1700
Data Index: 631377 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 1990940 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6750. Min Act: -0.1700
Data Index: 3972787 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 8562842 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6750. Min Act: -0.1700
Data Index: 3315100 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 24608 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 2997987 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 1994921 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 4853550 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 4850911 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 6170964 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 1186016 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 1941897 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5500. Min Act: -0.1700
Data Index: 7160486 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 2422405 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19