Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.5688. Min Act: -0.1700
Data Index: 5372184 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.4126. Min Act: -0.1700
Data Index: 641935 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.3501. Min Act: -0.1700
Data Index: 7732253 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.3501. Min Act: -0.1700
Data Index: 3256255 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.3501. Min Act: -0.1700
Data Index: 8577798 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.3188. Min Act: -0.1700
Data Index: 8344459 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.3188. Min Act: -0.1700
Data Index: 1392052 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.3188. Min Act: -0.1700
Data Index: 1072113 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.2876. Min Act: -0.1700
Data Index: 274043 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.2563. Min Act: -0.1700
Data Index: 7331348 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.2251. Min Act: -0.1700
Data Index: 8102064 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.1938. Min Act: -0.1700
Data Index: 4954762 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.1626. Min Act: -0.1700
Data Index: 3456683 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.1001. Min Act: -0.1700
Data Index: 6514949 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.1001. Min Act: -0.1700
Data Index: 7263508 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.0688. Min Act: -0.1700
Data Index: 7370910 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.1001. Min Act: -0.1700
Data Index: 2626040 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.1001. Min Act: -0.1700
Data Index: 4878204 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.0688. Min Act: -0.1700
Data Index: 7109582 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5688. Min Range: -5.5688
Max Act: 5.0688. Min Act: -0.1700
Data Index: 1259859 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19