Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.9745. Min Act: -0.1700
Data Index: 6806836 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.9120. Min Act: -0.1700
Data Index: 432569 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.8807. Min Act: -0.1700
Data Index: 1761798 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.8495. Min Act: -0.1700
Data Index: 3148112 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.8182. Min Act: -0.1700
Data Index: 1458952 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.8182. Min Act: -0.1700
Data Index: 3050818 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.7557. Min Act: -0.1700
Data Index: 2569829 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.7557. Min Act: -0.1700
Data Index: 4321516 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.7245. Min Act: -0.1700
Data Index: 5792791 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.6620. Min Act: -0.1700
Data Index: 7782213 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.6307. Min Act: -0.1700
Data Index: 6898063 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.6620. Min Act: -0.1700
Data Index: 4835247 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.6307. Min Act: -0.1700
Data Index: 8431523 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.6620. Min Act: -0.1700
Data Index: 2227549 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.6307. Min Act: -0.1700
Data Index: 6853570 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.5995. Min Act: -0.1700
Data Index: 3533703 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.5995. Min Act: -0.1700
Data Index: 5612973 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.5682. Min Act: -0.1700
Data Index: 3743535 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.5682. Min Act: -0.1700
Data Index: 8604400 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9745. Min Range: -6.9745
Max Act: 6.5682. Min Act: -0.1700
Data Index: 4535042 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19