Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4133 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6782. Min Range: -10.6782
Max Act: 10.6782. Min Act: -0.1700
Data Index: 4924354 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6782. Min Range: -10.6782
Max Act: 10.3032. Min Act: -0.1700
Data Index: 6116050 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6782. Min Range: -10.6782
Max Act: 10.3032. Min Act: -0.1700
Data Index: 8573765 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6782. Min Range: -10.6782
Max Act: 10.2407. Min Act: -0.1700
Data Index: 3788009 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6782. Min Range: -10.6782
Max Act: 10.1782. Min Act: -0.1700
Data Index: 5306091 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6782. Min Range: -10.6782
Max Act: 10.1782. Min Act: -0.1700
Data Index: 4151115 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6782. Min Range: -10.6782
Max Act: 10.0532. Min Act: -0.1700
Data Index: 91639 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.9282. Min Act: -0.1700
Data Index: 370162 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.9282. Min Act: -0.1700
Data Index: 6228631 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.8657. Min Act: -0.1700
Data Index: 2468005 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.8657. Min Act: -0.1700
Data Index: 2377377 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.8657. Min Act: -0.1700
Data Index: 2126946 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.8032. Min Act: -0.1700
Data Index: 3266909 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.7407. Min Act: -0.1700
Data Index: 1480861 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.6782. Min Act: -0.1700
Data Index: 8051275 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.6157. Min Act: -0.1700
Data Index: 8237358 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.6157. Min Act: -0.1700
Data Index: 4205637 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.6157. Min Act: -0.1700
Data Index: 4254769 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.6157. Min Act: -0.1700
Data Index: 7511150 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6782. Min Range: -10.6782
Max Act: 9.6157. Min Act: -0.1700
Data Index: 1592532 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19