Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4695 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.3558. Min Act: -0.1700
Data Index: 328086 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0745. Min Act: -0.1700
Data Index: 3379057 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0120. Min Act: -0.1700
Data Index: 4817629 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0120. Min Act: -0.1700
Data Index: 6949684 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3558. Min Range: -5.3558
Max Act: 5.0120. Min Act: -0.1700
Data Index: 1856566 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.9183. Min Act: -0.1700
Data Index: 5696754 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8870. Min Act: -0.1700
Data Index: 6330912 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8870. Min Act: -0.1700
Data Index: 3409655 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8870. Min Act: -0.1700
Data Index: 3821732 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8558. Min Act: -0.1700
Data Index: 3193555 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8870. Min Act: -0.1700
Data Index: 7780243 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8558. Min Act: -0.1700
Data Index: 357963 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8558. Min Act: -0.1700
Data Index: 8562462 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8245. Min Act: -0.1700
Data Index: 5000917 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8245. Min Act: -0.1700
Data Index: 8396182 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8245. Min Act: -0.1700
Data Index: 947583 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8558. Min Act: -0.1700
Data Index: 3051736 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8245. Min Act: -0.1700
Data Index: 6586516 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8245. Min Act: -0.1700
Data Index: 8162070 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3558. Min Range: -5.3558
Max Act: 4.8245. Min Act: -0.1700
Data Index: 1137142 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19